Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

DeepSeek v4 Flash experimental with vision running (fast) on an m5 max computer and analyzing an image. The implementation for Metal / CUDA / ROCm is finished, just doing the last tests today before releasing it.

antirez

79,967 subscribers

59,411 views • 2 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

GLM 5.2 flash Q2 (generated by myself with similar recipe of DS4 Flash of DwarfStar GGUF) running on an M5 Max with 128GB. The Q4 weights also work on tensor parallel inference in two M5 Max systems. Soon on GitHub. Still testing + CUDA + ROCm ...

GLM 5.2 flash Q2 (generated by myself with similar recipe of DS4 Flash of DwarfStar GGUF) running on an M5 Max with 128GB. The Q4 weights also work on tensor parallel inference in two M5 Max systems. Soon on GitHub. Still testing + CUDA + ROCm ...

antirez

28,103 views • 7 days ago

DeepSeek v4 PRO running via SSD streaming on my 128GB MacBook m5 max. 1.6 trillion parameters.

DeepSeek v4 PRO running via SSD streaming on my 128GB MacBook m5 max. 1.6 trillion parameters.

antirez

275,713 views • 3 months ago

GLM 5.2, Q2_K routed experts (effectively ~2.6 bits) running with SSD streaming on an M5 Max 128GB computer.

GLM 5.2, Q2_K routed experts (effectively ~2.6 bits) running with SSD streaming on an M5 Max 128GB computer.

antirez

318,863 views • 2 months ago

DwarfStar with vision support for GLM 5.3 running on a MacBook m5max computer. The vision support is *not* quantized for max precision for now.

DwarfStar with vision support for GLM 5.3 running on a MacBook m5max computer. The vision support is not quantized for max precision for now.

antirez

22,187 views • 5 days ago

Timelapse #177 (14 hrs) - Picked up an RTX Pro 6000 Blackwell and wired in another 1000W PSU - running two of them now - DeepSeek v4 Flash running locally on both GPUs - Distilling DeepSeek v4 Flash down into Nanbeige (still cooking) - Kernel bench runs for DeepSeek v4 Flash and Qwen 3.8 Max - Got it into chat but couldn't reliably get it into the OMP harness yet - Private contract work - days like this are stuff I actually want to build. and when it's the high-intensity grind, i still have to show up and get it done

Timelapse #177 (14 hrs) - Picked up an RTX Pro 6000 Blackwell and wired in another 1000W PSU - running two of them now - DeepSeek v4 Flash running locally on both GPUs - Distilling DeepSeek v4 Flash down into Nanbeige (still cooking) - Kernel bench runs for DeepSeek v4 Flash and Qwen 3.8 Max - Got it into chat but couldn't reliably get it into the OMP harness yet - Private contract work - days like this are stuff I actually want to build. and when it's the high-intensity grind, i still have to show up and get it done

Elliot Arledge

17,401 views • 1 month ago

I didn't expect DeepSeek v4 PRO (not Flash) to run well on the Mac Studio M3 Ultra with 512GB of RAM. This is 2 bit quantized with the same DwarfStar recipe used for Flash. 433GB GGUF file. 130 t/s prefill, 13 t/s generation. Prefill in the video is low because small prompt.

I didn't expect DeepSeek v4 PRO (not Flash) to run well on the Mac Studio M3 Ultra with 512GB of RAM. This is 2 bit quantized with the same DwarfStar recipe used for Flash. 433GB GGUF file. 130 t/s prefill, 13 t/s generation. Prefill in the video is low because small prompt.

antirez

171,478 views • 3 months ago

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 views • 3 months ago

DGX Station: this is just the start of what it is possible to do (and why I claim DwarfStar could be *the* Station inference engine). DeepSeek v4 PRO Q2 with routed experts split among VRAM / RAM with kernels optimized for this peculiar setup. 45 t/s but can go faster.

DGX Station: this is just the start of what it is possible to do (and why I claim DwarfStar could be the Station inference engine). DeepSeek v4 PRO Q2 with routed experts split among VRAM / RAM with kernels optimized for this peculiar setup. 45 t/s but can go faster.

antirez

41,545 views • 18 days ago

DeepSeek V4 Flash + LFM2.5-VL-3B as the vision auxiliary in Hermes Agent is a deadly combo. DeepSeek handles the agentic work. LFM2.5-VL-3B gives it the eyes. I told it to use only its local vision model to browse. It read Hacker News, picked the top story, opened the eclipse map, found an Iceland webcam marker and opened the live feed. Every step seen through a 3B model running locally. No cloud vision API.

DeepSeek V4 Flash + LFM2.5-VL-3B as the vision auxiliary in Hermes Agent is a deadly combo. DeepSeek handles the agentic work. LFM2.5-VL-3B gives it the eyes. I told it to use only its local vision model to browse. It read Hacker News, picked the top story, opened the eclipse map, found an Iceland webcam marker and opened the live feed. Every step seen through a 3B model running locally. No cloud vision API.

Noctus

67,536 views • 22 days ago

Okay… DeepSeek V4 Flash actually COOKED 😭 With OpenCode, I’d place it around GPT-5.6 Terra Max—and definitely above Luna Max in this test. Almost unlimited usage for around €9, by the way. This model is a MASSIVE success. Just don’t use the wrong harness.

Okay… DeepSeek V4 Flash actually COOKED 😭 With OpenCode, I’d place it around GPT-5.6 Terra Max—and definitely above Luna Max in this test. Almost unlimited usage for around €9, by the way. This model is a MASSIVE success. Just don’t use the wrong harness.

OmedTheVibeCoder

35,417 views • 1 month ago

Running Qwen3.6 35B (vision) on 2 x M5 Max MacBook Pro with RDMA over Thunderbolt 5. It describes the image and identifies Apple Park correctly, but misidentifies John Ternus as Jeff Williams. Near instant response with prefix caching.

Running Qwen3.6 35B (vision) on 2 x M5 Max MacBook Pro with RDMA over Thunderbolt 5. It describes the image and identifies Apple Park correctly, but misidentifies John Ternus as Jeff Williams. Near instant response with prefix caching.

Alex Cheema

99,474 views • 4 months ago

Building another Autonomous Computer with 2x RTX PRO 6000 Blackwell. This is the ideal personal AI datacenter: 192 GB of VRAM on your desk. We're seeing ~300 tok/s with DeepSeek V4 Flash running locally. Own your compute. Own your intelligence.

Building another Autonomous Computer with 2x RTX PRO 6000 Blackwell. This is the ideal personal AI datacenter: 192 GB of VRAM on your desk. We're seeing ~300 tok/s with DeepSeek V4 Flash running locally. Own your compute. Own your intelligence.

Dee

32,160 views • 16 days ago

That's a bit slow. Streaming directly the K3 official hugging face 1.6TB of weights in mxfp4 in an m5 max 128gb.

That's a bit slow. Streaming directly the K3 official hugging face 1.6TB of weights in mxfp4 in an m5 max 128gb.

antirez

294,029 views • 1 month ago

DS4 running on DGX Spark (GB10 / CUDA), private branch for now. 12 tokens/sec, the memory bandwidth is limited in this system, at 270GB/sec. But prefill is ways more alighed to M3 Max at ~200 t/s. I'll release when more mature, but it is almost sure that it will get merged.

DS4 running on DGX Spark (GB10 / CUDA), private branch for now. 12 tokens/sec, the memory bandwidth is limited in this system, at 270GB/sec. But prefill is ways more alighed to M3 Max at ~200 t/s. I'll release when more mature, but it is almost sure that it will get merged.

antirez

84,127 views • 3 months ago

YOUR PARENTS PAID FOR THE CUDA MOAT! The #1 contributor to the CUDA MOAT isn't the the developers at NVIDIA, but it is the millions of developers outside of NVIDIA that invent new algorithms for CUDA like Flash Attention. For most of them, it started with an GeForce gaming GPU. NVIDIA is the only companies that has an reasonable good developer stack on consumer grade GPUs. As people grow up beyond playing CSGO & League of Legends & Minecraft, they either become anime weeaboos or they start programming on their existing computer with has an GeForce GPU

YOUR PARENTS PAID FOR THE CUDA MOAT! The #1 contributor to the CUDA MOAT isn't the the developers at NVIDIA, but it is the millions of developers outside of NVIDIA that invent new algorithms for CUDA like Flash Attention. For most of them, it started with an GeForce gaming GPU. NVIDIA is the only companies that has an reasonable good developer stack on consumer grade GPUs. As people grow up beyond playing CSGO & League of Legends & Minecraft, they either become anime weeaboos or they start programming on their existing computer with has an GeForce GPU

SemiAnalysis

25,230 views • 4 months ago

Crazy prefill speed of DwarfStar running DeepSeek v4 PRO in the DGX Station (private branch for now) using techniques that leverage the peculiar RAM + VRAM mixed setup of the Station. 3000 t/s but even more can be reached.

Crazy prefill speed of DwarfStar running DeepSeek v4 PRO in the DGX Station (private branch for now) using techniques that leverage the peculiar RAM + VRAM mixed setup of the Station. 3000 t/s but even more can be reached.

antirez

62,001 views • 16 days ago

HERMES DESKTOP APP JUST GOT A NEW ULTRA MODE FOR DEEPSEEK V4 PRO – AND IT COSTS ABOUT $1 A DAY TO RUN If you're using Hermes desktop app, you're probably already running DeepSeek – it's one of the top models available. The update: → DeepSeek V4 Pro now has thinking mode, fast mode, and a brand new ultra mode → There's also an extra high mode, but the real upgrade is ultra The actual cost: roughly $1/day for a normal workflow. That's about $20-25/month – basically the same as before, just with a significantly faster mode unlocked. The verdict after a full day of testing: it flies through tool calling. Noticeably faster, same price range. If you're already paying for DeepSeek through Hermes, this is a free upgrade sitting in your settings right now. Update Hermes, grab the DeepSeek API if you don't have it yet, and try V4 Pro on ultra. Bookmark this, you'll want to come back to it later.

SCOTTY BEAM

24,032 views • 1 month ago

Qwen3-Coder-Flash runs quite fast on an M4 Max with mlx-lm. Running the 4-bit here, generated 4,467 tokens at >107 tokens/sec:

Qwen3-Coder-Flash runs quite fast on an M4 Max with mlx-lm. Running the 4-bit here, generated 4,467 tokens at >107 tokens/sec:

Awni Hannun

196,508 views • 1 year ago

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.

23,951 views • 6 days ago

Loading DeepSeek v4 Flash just reminded me how good and fast this model is and how well it runs on DGX Sparks. GLM-5.2 is really awesome, but if you want fast and concurrent inference, DS4F is still a top choice IMO. Created by DS4F in single shot The coffee guy

Loading DeepSeek v4 Flash just reminded me how good and fast this model is and how well it runs on DGX Sparks. GLM-5.2 is really awesome, but if you want fast and concurrent inference, DS4F is still a top choice IMO. Created by DS4F in single shot The coffee guy

Mia

39,686 views • 1 month ago