Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Qwen 27B and Deepseek v4 Flash models working together on a single Lucebox machine, thats the beauty of having a discrete GPU paired with an unified access memory. A lot of space + good FLOPS & bandwidth. Working hard to increase concurrency performance on heterogeneous setups 🏎️

mrciffa

1,565 subscribers

10,908 просмотров • 6 дней назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

My first long form video on @x! I'm testing DeepSeek V4 Flash inside of Codex and doing a pull request with it to see if it's any good.

My first long form video on @x! I'm testing DeepSeek V4 Flash inside of Codex and doing a pull request with it to see if it's any good.

Gui Bibeau e/acc

14,343 просмотров • 1 месяц назад

Hopefully deepseek-v4.1-flash-expires-on-0910 releases soon.. This is really a step up in general and will put A LOT of pressure on Qwen Flash Next. It's doing a really good job on 0 shots, camera in this is shaky but that's easy to fix.

Hopefully deepseek-v4.1-flash-expires-on-0910 releases soon.. This is really a step up in general and will put A LOT of pressure on Qwen Flash Next. It's doing a really good job on 0 shots, camera in this is shaky but that's easy to fix.

Loktar 🇺🇸

17,002 просмотров • 13 дней назад

glm 5.3 vs qwen 3.8 vs gemini 3.7 vs deepseek v4 flash four models designed and built three structures each on a physics-backed site, with no dimensions anywhere in the brief the setup: our own agent loop on OpenRouter, a construction site as the tool set – footings, walls, arches, roofs, scaffold, a lamp. the site enforces physics and nothing else: unsupported brick falls, a roof needs walls under it, a worker reaches 3.2 m above whatever he stands on, an arch needs centring until the keystone is set, concrete cures before it carries. no budget ceiling – material cost is tallied and reported, never blocked. tasks: 1. house – a plot and a palette, no plan. shape, height and material are the model's call 2. lighthouse – a headland cut by a gully, with a rock stack standing 30 m offshore. the lamp must burn, it must be the highest thing built, and the keeper must be able to walk to it 3. bridge – a river with one islet and banks at different heights. cross it however you want models: Z.ai glm 5.3 flash, Qwen qwen 3.8 flash, Google DeepMind gemini 3.7 flash, DeepSeek v4 flash vision all twelve objects were finished and signed off by the models themselves. tallest lighthouse is qwen's at 38.4 m, planted on the offshore stack with a bridge run out to it – the only model that read the site that way. deepseek signed off its bridge on an empty riverbed: 0 bricks, 107 minutes, $1.16m of material tallied - total cost, three builds #1 glm 5.3 flash – $0.201 #2 gemini 3.7 flash – $0.871 #3 qwen 3.8 flash – $1.058 #4 deepseek v4 flash – $1.567 - wall clock, three builds #1 gemini 3.7 flash – 91m #2 glm 5.3 flash – 228m #3 deepseek v4 flash – 502m #4 qwen 3.8 flash – 912m - total tokens #1 gemini 3.7 flash – 3,567,052 #2 glm 5.3 flash – 4,732,748 #3 qwen 3.8 flash – 13,469,333 #4 deepseek v4 flash – 18,230,076 - defects logged by the site #1 deepseek v4 flash – 59 #2 gemini 3.7 flash – 132 #3 glm 5.3 flash – 221 #4 qwen 3.8 flash – 350 - material tallied across three builds #1 gemini 3.7 flash – $359,884 #2 glm 5.3 flash – $583,358 #3 deepseek v4 flash – $1,327,484 #4 qwen 3.8 flash – $2,188,625 observations: • glm is the cheap one and nothing here is close – $0.201 for three buildings, $0.042 per million tokens, 6x under gemini's rate • what glm spends it on is bulk, not care: 166,228 bricks in one house and 156 defect weight, the worst single object in the set • gemini is the efficiency line – 91 minutes and 3.57m tokens for all three and an eighth of qwen's clock • gemini also builds the smallest of everything. its lighthouse is 22.5 m against qwen's 38.4, its house 6.9 m against 19.3 • qwen is the maximalist: 1.18m bricks, $2.19m of material, tallest on all three tasks, and 912 minutes – 15 hours – to get there conclusion: twelve finished objects for $3.80 all in, and a 7.8x price spread between the cheapest model and the priciest! follow thehype. for 24/7 ai news, analysis and breakdowns

glm 5.3 vs qwen 3.8 vs gemini 3.7 vs deepseek v4 flash four models designed and built three structures each on a physics-backed site, with no dimensions anywhere in the brief the setup: our own agent loop on OpenRouter, a construction site as the tool set – footings, walls, arches, roofs, scaffold, a lamp. the site enforces physics and nothing else: unsupported brick falls, a roof needs walls under it, a worker reaches 3.2 m above whatever he stands on, an arch needs centring until the keystone is set, concrete cures before it carries. no budget ceiling – material cost is tallied and reported, never blocked. tasks: 1. house – a plot and a palette, no plan. shape, height and material are the model's call 2. lighthouse – a headland cut by a gully, with a rock stack standing 30 m offshore. the lamp must burn, it must be the highest thing built, and the keeper must be able to walk to it 3. bridge – a river with one islet and banks at different heights. cross it however you want models: Z.ai glm 5.3 flash, Qwen qwen 3.8 flash, Google DeepMind gemini 3.7 flash, DeepSeek v4 flash vision all twelve objects were finished and signed off by the models themselves. tallest lighthouse is qwen's at 38.4 m, planted on the offshore stack with a bridge run out to it – the only model that read the site that way. deepseek signed off its bridge on an empty riverbed: 0 bricks, 107 minutes, $1.16m of material tallied - total cost, three builds #1 glm 5.3 flash – $0.201 #2 gemini 3.7 flash – $0.871 #3 qwen 3.8 flash – $1.058 #4 deepseek v4 flash – $1.567 - wall clock, three builds #1 gemini 3.7 flash – 91m #2 glm 5.3 flash – 228m #3 deepseek v4 flash – 502m #4 qwen 3.8 flash – 912m - total tokens #1 gemini 3.7 flash – 3,567,052 #2 glm 5.3 flash – 4,732,748 #3 qwen 3.8 flash – 13,469,333 #4 deepseek v4 flash – 18,230,076 - defects logged by the site #1 deepseek v4 flash – 59 #2 gemini 3.7 flash – 132 #3 glm 5.3 flash – 221 #4 qwen 3.8 flash – 350 - material tallied across three builds #1 gemini 3.7 flash – $359,884 #2 glm 5.3 flash – $583,358 #3 deepseek v4 flash – $1,327,484 #4 qwen 3.8 flash – $2,188,625 observations: • glm is the cheap one and nothing here is close – $0.201 for three buildings, $0.042 per million tokens, 6x under gemini's rate • what glm spends it on is bulk, not care: 166,228 bricks in one house and 156 defect weight, the worst single object in the set • gemini is the efficiency line – 91 minutes and 3.57m tokens for all three and an eighth of qwen's clock • gemini also builds the smallest of everything. its lighthouse is 22.5 m against qwen's 38.4, its house 6.9 m against 19.3 • qwen is the maximalist: 1.18m bricks, $2.19m of material, tallest on all three tasks, and 912 minutes – 15 hours – to get there conclusion: twelve finished objects for $3.80 all in, and a 7.8x price spread between the cheapest model and the priciest! follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

26,360 просмотров • 24 дней назад

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.

BridgeMind

70,626 просмотров • 3 месяцев назад

Most of the world's energy flows through heterogeneous hardware, yet today's AI software is designed for homogeneous and centralized setups. The concentration of high-performance AI into the hands of a few powerful entities poses profound risks to humanity. Introducing Dnet: a unified ML compiler and runtime that unlocks heterogeneous hardware, turning every stranded energy unit into fuel for intelligence. Compile once and deploy anywhere, built on Solana.

Most of the world's energy flows through heterogeneous hardware, yet today's AI software is designed for homogeneous and centralized setups. The concentration of high-performance AI into the hands of a few powerful entities poses profound risks to humanity. Introducing Dnet: a unified ML compiler and runtime that unlocks heterogeneous hardware, turning every stranded energy unit into fuel for intelligence. Compile once and deploy anywhere, built on Solana.

Dria

33,175 просмотров • 1 год назад

$INFQ GPU + CPU + QPU Frontier models are hitting saturation on tokens (data volume) and context windows (memory). $INFQ CTO walks through how they and $NVDA are working together to add a Quantum Processing Unit to the chain as the next inflection point.

$INFQ GPU + CPU + QPU Frontier models are hitting saturation on tokens (data volume) and context windows (memory). $INFQ CTO walks through how they and $NVDA are working together to add a Quantum Processing Unit to the chain as the next inflection point.

YeahDave

57,181 просмотров • 4 месяцев назад

Slowly adding to my tool stack for Hallway . This is a spline patch making a mesh that is wrapped from UV space onto the model. There's also setups to unwrap meshes on the surface back to UV space. Working in UV space enables a lot of procedural workflows. #b3d

Slowly adding to my tool stack for Hallway . This is a spline patch making a mesh that is wrapped from UV space onto the model. There's also setups to unwrap meshes on the surface back to UV space. Working in UV space enables a lot of procedural workflows. #b3d

aVersionOfReality

81,464 просмотров • 3 лет назад

.Sam Altman says OpenAI will "obviously" have a version of Codex that "can do other knowledge-work tasks, and control your computer." "Of course we should have an ability to kick off new tasks from mobile, and we'll do that." "Really what you want is your single AI that's working for you on a unified backend. Access to all your data and ideas, and your stuff and your memory, and the ability to work across a lot of surfaces."

.Sam Altman says OpenAI will "obviously" have a version of Codex that "can do other knowledge-work tasks, and control your computer." "Of course we should have an ability to kick off new tasks from mobile, and we'll do that." "Really what you want is your single AI that's working for you on a unified backend. Access to all your data and ideas, and your stuff and your memory, and the ability to work across a lot of surfaces."

TBPN

109,046 просмотров • 6 месяцев назад

SK Hynix's Hoshik Kim admits high bandwidth memory "is not the answer" to the memory-wall problem, and SK is working on different solutions to solve the bottleneck. "No, actually, I kind of agree with Pat. So HBM is not the answer." [SK Hynix is admitting that HBM is a bad memory?] "Nothing is a bad memory. It's a good memory, but it's not the final answer. So actually, HBM will not solve the memory-wall problem. Memory-wall problem is an inherent AI problem, which you cannot avoid." "So we try our best to provide higher bandwidth with this memory, with HBM technology even though it has some limitation, as Pat already mentioned, with thermal, IOs, cost, a lot of stuff. "But that's the only thing we got right now to help ease this memory-wall problem, memory-bottleneck problem. But at the same time, we are working in different directions to solve this memory-wall problem with different solutions."

SK Hynix's Hoshik Kim admits high bandwidth memory "is not the answer" to the memory-wall problem, and SK is working on different solutions to solve the bottleneck. "No, actually, I kind of agree with Pat. So HBM is not the answer." [SK Hynix is admitting that HBM is a bad memory?] "Nothing is a bad memory. It's a good memory, but it's not the final answer. So actually, HBM will not solve the memory-wall problem. Memory-wall problem is an inherent AI problem, which you cannot avoid." "So we try our best to provide higher bandwidth with this memory, with HBM technology even though it has some limitation, as Pat already mentioned, with thermal, IOs, cost, a lot of stuff. "But that's the only thing we got right now to help ease this memory-wall problem, memory-bottleneck problem. But at the same time, we are working in different directions to solve this memory-wall problem with different solutions."

Fireside Alpha

140,571 просмотров • 1 месяц назад

You can now run Qwen 3.6 27B on <10GB of memory and retain 90% of the intelligence. Today, PrismML dropped Bonsai 27B - which takes their unique compression approach they have already successfully applied to Qwen3.6 8B and Flux2-Klein and applied it to a properly smart model. Here is it using an entire computer for deep research. Long horizon agentic calls already are strong with Qwen3.6 27B and they still are here - just on 10x less memory.

You can now run Qwen 3.6 27B on <10GB of memory and retain 90% of the intelligence. Today, PrismML dropped Bonsai 27B - which takes their unique compression approach they have already successfully applied to Qwen3.6 8B and Flux2-Klein and applied it to a properly smart model. Here is it using an entire computer for deep research. Long horizon agentic calls already are strong with Qwen3.6 27B and they still are here - just on 10x less memory.

Tim Carambat

63,449 просмотров • 2 месяцев назад

qwen 3.8 max vs deepseek v4 flash 0731 vs kimi k3 vs gpt 5.6 sol – on rubik's cube and chess four frontier models built a rubik's cube stand and solved it, then built a chess board and played claude opus 5 on it the setup: Nous Research's hermes agent cli on OpenRouter tasks: 1. cube – build a 3d rubik's cube with a cli and a Three.js viewer, then solve an identical scrambled position on your own stand 2. chess – build a 3d chess stand, then play white against claude opus 5 as black, live, one move at a time. no engine, no solver, no opening book on either side. stockfish depth 14 grades every chess ply afterwards; neither player sees the score models: DeepSeek v4 flash 0731, OpenAI gpt-5.6 sol, Kimi.ai kimi k3, Qwen qwen 3.8 max gpt-5.6 sol and deepseek v4 flash solved their cubes – sol in 24 moves and seventeen seconds, deepseek in 32. qwen and kimi never got there, giving up at 96 and 207 moves then all four built chess stands and played white against claude opus 5 on them, and all four resigned: deepseek on move 13, sol on 19, kimi on 21, qwen holding out longest at 29 - build time, both stands #1 gpt-5.6 sol – 16m 43s #2 deepseek v4 flash – 97m 39s #3 kimi k3 – 166m 09s #4 qwen 3.8 max – 215m 08s - build attempts before a working stand #1 gpt-5.6 sol – 3 #2 qwen 3.8 max – 4 #3 kimi k3 – 4 #4 deepseek v4 flash – 5 - total tokens #1 gpt-5.6 sol – 6,713,754 #2 qwen 3.8 max – 17,272,507 #3 kimi k3 – 22,427,504 #4 deepseek v4 flash – 27,417,442 - total price #1 deepseek v4 flash – $0.557 #2 gpt-5.6 sol – $6.319 #3 qwen 3.8 max – $10.270 #4 kimi k3 – $16.667 observations: • deepseek v4 flash is the cheapest model here by a margin nobody else is near, and it got there while being the least efficient of the four. it burned 27.4m tokens – more than anyone, 5m more than kimi – and still finished both benchmarks for $0.557. that is $0.02 per million tokens against kimi's $0.74. it also needed the most passes to produce working stands, five, and that did not matter: all five deepseek passes together cost a thirtieth of kimi's two • so what deepseek cannot do is get it right the first time. what it can do is get it right the fifth time, for half a dollar. that is a different thing to be buying – not a good first draft, but the option to keep asking • gpt-5.6 sol is the opposite profile and the strongest of the four on pure efficiency. 16m 43s to build both stands, 6.7m tokens, three passes – under 40% of the next lowest token count and a quarter of deepseek's, on an eighth of qwen's clock. it also solved the cube fastest of anyone, 24 moves in seventeen seconds. sol is what you reach for when you want the answer now and can absorb $0.94 per million • sol's weakness is in what it does not check. its chess viewer deleted the capturing piece instead of the captured one, so pieces disappeared off the board mid-game – a defect the fifty-cent deepseek stand did not have. fast and terse turns out to be the same dial as fast and unverified • qwen 3.8 max is not the cheap open-weights option it gets treated as. $10.270 across the two benchmarks, second most expensive of the four, 18x deepseek, and by a distance the slowest – 215 minutes of build time, nearly thirteen times sol's. what the money buys is judgment: it played eighteen moves without a single error worth a hundredth of a pawn, then made exactly one bad move in the whole game, and averaged 44.6 centipawns lost across the longest game any of the four managed. it also could not solve a rubik's cube in 96 tries • kimi k3 is the one line with no reading that flatters it. most expensive at $16.667, last on the cube at 207 moves, last at chess at 478 centipawns lost per move. it is also the model that verified hardest – on the cube it wrote its own integrity check instead of trusting its output. that makes the result worse rather than better: the checking was real, and the reasoning underneath it still was not follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

84,777 просмотров • 1 месяц назад

For anyone wandering what does it mean to run ds4-agent locally on an M5 Max using DeepSeek V4 Flash q2-imatrix gguf model. Here's a video of ds4 updating itself, adding a way to leverage HF_HOME for gguf models. Future of Local AI is bright!

For anyone wandering what does it mean to run ds4-agent locally on an M5 Max using DeepSeek V4 Flash q2-imatrix gguf model. Here's a video of ds4 updating itself, adding a way to leverage HF_HOME for gguf models. Future of Local AI is bright!

Ivan Fioravanti ᯅ

30,452 просмотров • 4 месяцев назад

UC Berkeley just open-sourced FreeToken. (2–4x faster local LLM inference than Ollama) the results are wild: - Qwen3.6-35B on an 8GB GPU at 39.3 tokens/s - DeepSeek-V4-Flash 284B on a 32GB GPU at 22 tokens/s - GLM-5.2 753B on a 96GB GPU at 14.9 tokens/s a 35B model at 16-bit precision needs about 70GB just for its weights. even at 4 bits it is close to 18GB, and FreeToken serves it on an 8GB GPU. let me explain how: all three models mentioned above are Mixture-of-Experts, and that is what FreeToken takes advantage of. each layer holds hundreds of separate experts plus a small router that picks a few of them per token. Qwen3.6-35B activates roughly 3B of its 35B parameters per token. DeepSeek-V4-Flash picks 6 of 256 experts per layer, so 13B of its 284B run at a time. so compute was never the bottleneck. the weights a single step touches fit comfortably on a consumer GPU. every expert the router might pick still has to exist somewhere. they sit in system RAM, and the GPU keeps a cache of the ones the model has been using recently. so everything comes down to what happens when the router picks an expert that is not on the GPU. there are two ways to serve that miss: 1. copy it over PCIe and run it on the GPU 2. run it on the CPU, where it already lives both read from the same system memory, so they compete for one pool of bandwidth instead of adding to each other. existing engines pick one option and freeze it when the model loads. but routing changes on every token, so a fixed choice misses most of what the model asks for. FreeToken measures both bandwidths on your machine and splits each step's misses between the two paths in proportion. the GPU and CPU results then merge exactly, with no approximation. two machines with the same GPU can end up wanting opposite strategies, which I did not expect. a 5090 in a gaming desktop should push nearly everything over PCIe, while an 8GB laptop is better off computing most misses on the CPU. none of that is readable off a spec sheet, so the engine profiles it once per machine. the second half of the design is about agents. coding agents constantly rewrite their own history, and every edit normally forces thousands of tokens back through prefill. FreeToken saves its checkpoints at the exact boundaries agent frameworks cut on, so it only reprocesses the new part. its slowest first token stays under 44 seconds, while llama.cpp peaks at 232 and KTransformers at 946. it serves the OpenAI and Anthropic APIs under Apache 2.0, so Claude Code and Codex can point at it directly. releasing weights publicly decides who can download a model, not who can afford to run one. frontier open models keep shipping, and running them still assumes a rented cluster. meanwhile there are over a hundred million consumer machines with discrete GPUs sitting mostly idle. closing that gap was never a hardware problem, and work like this is what turns open weights into something you can actually use. paper: repo: almost every idea in this post, from why memory bandwidth decides the outcome to why moving weights costs more than computing on them, comes straight out of how a GPU is built. I wrote a detailed primer on that. the article is quoted below.

UC Berkeley just open-sourced FreeToken. (2–4x faster local LLM inference than Ollama) the results are wild: - Qwen3.6-35B on an 8GB GPU at 39.3 tokens/s - DeepSeek-V4-Flash 284B on a 32GB GPU at 22 tokens/s - GLM-5.2 753B on a 96GB GPU at 14.9 tokens/s a 35B model at 16-bit precision needs about 70GB just for its weights. even at 4 bits it is close to 18GB, and FreeToken serves it on an 8GB GPU. let me explain how: all three models mentioned above are Mixture-of-Experts, and that is what FreeToken takes advantage of. each layer holds hundreds of separate experts plus a small router that picks a few of them per token. Qwen3.6-35B activates roughly 3B of its 35B parameters per token. DeepSeek-V4-Flash picks 6 of 256 experts per layer, so 13B of its 284B run at a time. so compute was never the bottleneck. the weights a single step touches fit comfortably on a consumer GPU. every expert the router might pick still has to exist somewhere. they sit in system RAM, and the GPU keeps a cache of the ones the model has been using recently. so everything comes down to what happens when the router picks an expert that is not on the GPU. there are two ways to serve that miss: 1. copy it over PCIe and run it on the GPU 2. run it on the CPU, where it already lives both read from the same system memory, so they compete for one pool of bandwidth instead of adding to each other. existing engines pick one option and freeze it when the model loads. but routing changes on every token, so a fixed choice misses most of what the model asks for. FreeToken measures both bandwidths on your machine and splits each step's misses between the two paths in proportion. the GPU and CPU results then merge exactly, with no approximation. two machines with the same GPU can end up wanting opposite strategies, which I did not expect. a 5090 in a gaming desktop should push nearly everything over PCIe, while an 8GB laptop is better off computing most misses on the CPU. none of that is readable off a spec sheet, so the engine profiles it once per machine. the second half of the design is about agents. coding agents constantly rewrite their own history, and every edit normally forces thousands of tokens back through prefill. FreeToken saves its checkpoints at the exact boundaries agent frameworks cut on, so it only reprocesses the new part. its slowest first token stays under 44 seconds, while llama.cpp peaks at 232 and KTransformers at 946. it serves the OpenAI and Anthropic APIs under Apache 2.0, so Claude Code and Codex can point at it directly. releasing weights publicly decides who can download a model, not who can afford to run one. frontier open models keep shipping, and running them still assumes a rented cluster. meanwhile there are over a hundred million consumer machines with discrete GPUs sitting mostly idle. closing that gap was never a hardware problem, and work like this is what turns open weights into something you can actually use. paper: repo: almost every idea in this post, from why memory bandwidth decides the outcome to why moving weights costs more than computing on them, comes straight out of how a GPU is built. I wrote a detailed primer on that. the article is quoted below.

Akshay 🚀

343,270 просмотров • 1 месяц назад

Every big MoE model I test on my 3090 is basically to see how good it is compared to Qwen3.6-27B. "How good is it compared to Qwen3.6-27B?" is the question I get asked the most, and that shows how much people love and, more importantly, trust the 27B 27B is battle tested. It has proven its worth and has nothing left to prove. Now it just needs to make way for the next 27B. Here’s an example video: a Three.js task, same prompt, not oneshot but two shots for all models. All ran on my 3090 + 64GB VRAM Qwen-3.6-27b fully on vram while others have experts offloaded to system ram. Pinned on the left: Qwen3.6-27B-Q5 On the right, i'm switching between Inkling-Small-Q4_K_M DSV4-Flash-0731-UD-IQ1 Ling-3.0-Flash-Q4_K_M Qwen3.6-27B nailed it. The effects and visuals are just spot on.The other models got some things right, but not everything. Second place would have to go to Inkling-Small while DSV4-Flash-0731 and Ling-3.0-Flash failed to capture the full requirements. This is also why we’re all excited for Qwen Qwen3.8-27B!

Every big MoE model I test on my 3090 is basically to see how good it is compared to Qwen3.6-27B. "How good is it compared to Qwen3.6-27B?" is the question I get asked the most, and that shows how much people love and, more importantly, trust the 27B 27B is battle tested. It has proven its worth and has nothing left to prove. Now it just needs to make way for the next 27B. Here’s an example video: a Three.js task, same prompt, not oneshot but two shots for all models. All ran on my 3090 + 64GB VRAM Qwen-3.6-27b fully on vram while others have experts offloaded to system ram. Pinned on the left: Qwen3.6-27B-Q5 On the right, i'm switching between Inkling-Small-Q4_K_M DSV4-Flash-0731-UD-IQ1 Ling-3.0-Flash-Q4_K_M Qwen3.6-27B nailed it. The effects and visuals are just spot on.The other models got some things right, but not everything. Second place would have to go to Inkling-Small while DSV4-Flash-0731 and Ling-3.0-Flash failed to capture the full requirements. This is also why we’re all excited for Qwen Qwen3.8-27B!

AJ

11,670 просмотров • 1 месяц назад

Qwopus 3.6-27b Coder I had a lot of requests to test it, so I did. I ran the same tests I’ve done on other models. It scored lower on tool-eval-bench than both Qwen 3.6 27b and Qwen 3.6 35b. It also produced broken single-file Tetris and Solar System HTML demos, even after 3 fresh attempts. In the Tetris html, the game stalled when you completed a line. It also randomly changed the pieces when moving them left or right. In the Solar System html, clicking on the sun or any planet broke the rendering — the objects just disappeared. Conclusion: The regular Qwen 3.6 27b and 35b models performed better. What do you think of Qwopus 3.6-27b Coder? Full results & RAW files: Full prompts in the posts below.

Qwopus 3.6-27b Coder I had a lot of requests to test it, so I did. I ran the same tests I’ve done on other models. It scored lower on tool-eval-bench than both Qwen 3.6 27b and Qwen 3.6 35b. It also produced broken single-file Tetris and Solar System HTML demos, even after 3 fresh attempts. In the Tetris html, the game stalled when you completed a line. It also randomly changed the pieces when moving them left or right. In the Solar System html, clicking on the sun or any planet broke the rendering — the objects just disappeared. Conclusion: The regular Qwen 3.6 27b and 35b models performed better. What do you think of Qwopus 3.6-27b Coder? Full results & RAW files: Full prompts in the posts below.

Mia

11,183 просмотров • 2 месяцев назад

NVIDIA'S BIGGEST COMPETITOR AMD BUILT A BOX THAT RUNS A 235B MODEL AND KILLS $200 OPENAI AND $200 CLAUDE CODE FOR $9 A MONTH amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on a single piece of silicon with 128gb of unified memory the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months ollama installs in one command and claude code points at localhost so nothing leaves the machine and nothing costs per request bookmark this and read the article below

NVIDIA'S BIGGEST COMPETITOR AMD BUILT A BOX THAT RUNS A 235B MODEL AND KILLS $200 OPENAI AND $200 CLAUDE CODE FOR $9 A MONTH amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on a single piece of silicon with 128gb of unified memory the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months ollama installs in one command and claude code points at localhost so nothing leaves the machine and nothing costs per request bookmark this and read the article below

starmex

93,580 просмотров • 3 месяцев назад

After an all-nighter, we got the first app working with Omagrid: OpenCode. Just boot into Omarchy. DeepSeek + Qwen are already there for all your apps and agents. It’s that simple. Want early access? DM me! PS: Omagrid is a P2P network. More Omarchy machines, more models.

After an all-nighter, we got the first app working with Omagrid: OpenCode. Just boot into Omarchy. DeepSeek + Qwen are already there for all your apps and agents. It’s that simple. Want early access? DM me! PS: Omagrid is a P2P network. More Omarchy machines, more models.

Dee

126,292 просмотров • 16 дней назад

"Love to have him back, I've told him that many times already. But at the same time, we've got a good group. They're working hard and doing a lot of good things." - Brian Flores on @HarriSmith22

"Love to have him back, I've told him that many times already. But at the same time, we've got a good group. They're working hard and doing a lot of good things." - Brian Flores on @HarriSmith22

Minnesota Vikings

73,778 просмотров • 3 месяцев назад

Please scrap this movie and move on, Salman Khan! I know you’ve put in a lot of hard work, but working hard on the wrong project won’t give you good results. It’s embarrassing.

Please scrap this movie and move on, Salman Khan! I know you’ve put in a lot of hard work, but working hard on the wrong project won’t give you good results. It’s embarrassing.

Being ADARSH⚡

39,742 просмотров • 21 дней назад