Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

One task, two models. GLM 5.3 Flash running slower at 25 tok/s prose Qwen3.8 Flash running faster at 47 tok/s prose Who will finish the task first?

Mia

40,222 subscribers

27,481 görüntüleme • 1 ay önce •via X (Twitter)

Bilim & Teknoloji Eğitim

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Okay, I guess I didn't waste all that money after all Deepseek V4.1 Flash 304 tok/s code, 135 tok/s prose Zero optimization, will have it max optimized by the morning.

Okay, I guess I didn't waste all that money after all Deepseek V4.1 Flash 304 tok/s code, 135 tok/s prose Zero optimization, will have it max optimized by the morning.

Killy

44,653 görüntüleme • 1 ay önce

100 tok/s on GLM-5.3-Flash, GLM-5.3 runs on the 6000s @ 80-180 tok/s I have not tried the Studio, I’m sure it’s an amazing machine especially if you are in the Mac world already. From a pure logistics POV the sparks use little power, make less noise, serve good model & tokens

100 tok/s on GLM-5.3-Flash, GLM-5.3 runs on the 6000s @ 80-180 tok/s I have not tried the Studio, I’m sure it’s an amazing machine especially if you are in the Mac world already. From a pure logistics POV the sparks use little power, make less noise, serve good model & tokens

0xSero

69,452 görüntüleme • 2 ay önce

DeepSeek V4 Flash Running 12 GB phone CPU only. - Model: 284B parameters - Speed: 1 tok/s - Just clever expert streaming from flash storage. -

DeepSeek V4 Flash Running 12 GB phone CPU only. - Model: 284B parameters - Speed: 1 tok/s - Just clever expert streaming from flash storage. -

Md Ismail Šojal 🕷️

28,301 görüntüleme • 2 ay önce

🚨Breaking: Ox Alpha is GLM 5.3 Flash by Z.ai! It's already available in Kilo, so we put it to the test. We gave the same prompt to both GLM 5.3 Flash and Gemini 3.7 Flash: Build a spectral audio visualizer. Costs: GLM 5.3 Flash: $0.01 Gemini 3.7 Flash: $0.17 17x cheaper for GLM 5.3 Flash. Who won on one-shot results?

🚨Breaking: Ox Alpha is GLM 5.3 Flash by Z.ai! It's already available in Kilo, so we put it to the test. We gave the same prompt to both GLM 5.3 Flash and Gemini 3.7 Flash: Build a spectral audio visualizer. Costs: GLM 5.3 Flash: $0.01 Gemini 3.7 Flash: $0.17 17x cheaper for GLM 5.3 Flash. Who won on one-shot results?

Kilo (acq. by Anaconda)

21,683 görüntüleme • 2 ay önce

4 DGX Sparks running DeepSeek V4.1 Flash 6 concurrent sessions, 170.73 tok/s coding throughput. 🔥 1,200 output tokens in 7.028 seconds. Warm single-stream: 💻 Code: 77.61 tok/s 🧮 Math: 74.08 🧠 Reasoning: 48.75 ✍️ Prose: 33.02 6-stream aggregate: 💻 Code: 170.73 tok/s 🔢 Counting: 291.64 tok/s 552B MoE · MXFP4 · TP4 · vLLM + DSpark + CUDA graphs ✅ Tool calling + vision ✅ 127,480-token retrieval test passed ✅ 300K configured context Video replays the actual recorded streams at 1× speed. Thinking OFF, 200-token cap per coding request. Short-prompt coding throughput Credit to Tech2Wild for the Boot9 recipe. NVIDIA AI

4 DGX Sparks running DeepSeek V4.1 Flash 6 concurrent sessions, 170.73 tok/s coding throughput. 🔥 1,200 output tokens in 7.028 seconds. Warm single-stream: 💻 Code: 77.61 tok/s 🧮 Math: 74.08 🧠 Reasoning: 48.75 ✍️ Prose: 33.02 6-stream aggregate: 💻 Code: 170.73 tok/s 🔢 Counting: 291.64 tok/s 552B MoE · MXFP4 · TP4 · vLLM + DSpark + CUDA graphs ✅ Tool calling + vision ✅ 127,480-token retrieval test passed ✅ 300K configured context Video replays the actual recorded streams at 1× speed. Thinking OFF, 200-token cap per coding request. Short-prompt coding throughput Credit to Tech2Wild for the Boot9 recipe. NVIDIA AI

Wësche

24,282 görüntüleme • 1 ay önce

Two models. One DGX Spark One identical voxel Eiffel Tower prompt. Qwen3.8-27B xhigh: 83K tokens, 41m29s, 33.4 tok/s Ornith 1.5 35B-A3B: 47K tokens, 10m35s, 74.0 tok/s Thinking on, no token ceiling, matched camera. Ornith finished much faster; Qwen spent far more tokens.

Two models. One DGX Spark One identical voxel Eiffel Tower prompt. Qwen3.8-27B xhigh: 83K tokens, 41m29s, 33.4 tok/s Ornith 1.5 35B-A3B: 47K tokens, 10m35s, 74.0 tok/s Thinking on, no token ceiling, matched camera. Ornith finished much faster; Qwen spent far more tokens.

Wësche

51,527 görüntüleme • 2 ay önce

Laguna XS 2.1 just matched Qwen 3.6 35B on a real coding task & ran twice as fast. > Same RTX 3090 > Laguna: 158 tok/s. Qwen: 81 tok/s The local model race isn't about size anymore. It's about who moves faster.

Laguna XS 2.1 just matched Qwen 3.6 35B on a real coding task & ran twice as fast. > Same RTX 3090 > Laguna: 158 tok/s. Qwen: 81 tok/s The local model race isn't about size anymore. It's about who moves faster.

0xMarioNawfal

63,839 görüntüleme • 3 ay önce

This is running on a 16gb mac mini and 3090 Incredible model beats most of the mid stuff, qwen3.8-next-flash in exl3-3bits over half the model is being streamed from NVME it's 31 tok/s that is faster than Codex as of late.. for 2600$ I feel like my mission needs updating

This is running on a 16gb mac mini and 3090 Incredible model beats most of the mid stuff, qwen3.8-next-flash in exl3-3bits over half the model is being streamed from NVME it's 31 tok/s that is faster than Codex as of late.. for 2600$ I feel like my mission needs updating

0xSero

17,695 görüntüleme • 20 gün önce

GLM-4.7 Flash by Z.ai running on M3 Ultra using MLX! 4bit at 81 toks/s 🔥 8bit at 64 toks/s 🔥 (video below) Model converted from transformers to MLX on the fly with Codex + GPT-5.2 HIgh!

GLM-4.7 Flash by Z.ai running on M3 Ultra using MLX! 4bit at 81 toks/s 🔥 8bit at 64 toks/s 🔥 (video below) Model converted from transformers to MLX on the fly with Codex + GPT-5.2 HIgh!

Ivan Fioravanti ᯅ

75,425 görüntüleme • 9 ay önce

RadixArkのQwen3.8-Flash-Next-NVFP4 つかってFreeTokenをcodexで改造してやっと良きスピード出た Activeが小さいからそれなりに速度出た RAM DDR5 8ch GPU - RTX5090 x1 Prefill 277.5 tok/s Decode 59.13 tok/s - RTX5090 x2 Prefill 619.5 tok/s Decode 83.14 tok/s

RadixArkのQwen3.8-Flash-Next-NVFP4 つかってFreeTokenをcodexで改造してやっと良きスピード出た Activeが小さいからそれなりに速度出た RAM DDR5 8ch GPU - RTX5090 x1 Prefill 277.5 tok/s Decode 59.13 tok/s - RTX5090 x2 Prefill 619.5 tok/s Decode 83.14 tok/s

ぱぷりか炒め

27,962 görüntüleme • 2 ay önce

Qwen3.8-Flash-Next is starting to feel like the local model Opus fans have been waiting for. Someone ran the NVFP4 176B-class Flash-Next on 2× DGX Sparks, and the results are wild. Real measured scaling → C1: 44.2 tok/s → C2: 64.6 tok/s → C4: 86.8 tok/s aggregate The per-stream speed drops with concurrency, but total throughput keeps climbing. Long-context behavior was even more impressive: → 5K: needle retrieved → 21K: needle retrieved → 84K: needle retrieved → 167K: needle retrieved → 262K: prefill succeeded, but the window was saturated That 167K retrieval test is the one I care about. Long agent runs are where models usually start losing the plot. Flash-Next didn’t. It also held up surprisingly well on physics-heavy reasoning, artifact generation, research workflows, evidence checking, and long-horizon planning. The personality is interesting too. DeepSeek V4 Flash feels like the dependable workhorse. GLM-5.2 feels like the problem-solving machine. Qwen3.8-Flash-Next feels more insightful. It has that rare ability to understand what you’re actually asking rather than just following the surface pattern. The main weakness I’ve noticed is instruction following. It can occasionally drift between prose turns where DeepSeek and GLM stay tighter. And this is why the 256GB M5 Ultra conversation gets interesting. If Apple can pair that huge unified-memory pool with enough bandwidth, this model class becomes genuinely practical for long-running local agents. We’re talking about frontier-class reasoning on hardware sitting on a desk.

Qwen3.8-Flash-Next is starting to feel like the local model Opus fans have been waiting for. Someone ran the NVFP4 176B-class Flash-Next on 2× DGX Sparks, and the results are wild. Real measured scaling → C1: 44.2 tok/s → C2: 64.6 tok/s → C4: 86.8 tok/s aggregate The per-stream speed drops with concurrency, but total throughput keeps climbing. Long-context behavior was even more impressive: → 5K: needle retrieved → 21K: needle retrieved → 84K: needle retrieved → 167K: needle retrieved → 262K: prefill succeeded, but the window was saturated That 167K retrieval test is the one I care about. Long agent runs are where models usually start losing the plot. Flash-Next didn’t. It also held up surprisingly well on physics-heavy reasoning, artifact generation, research workflows, evidence checking, and long-horizon planning. The personality is interesting too. DeepSeek V4 Flash feels like the dependable workhorse. GLM-5.2 feels like the problem-solving machine. Qwen3.8-Flash-Next feels more insightful. It has that rare ability to understand what you’re actually asking rather than just following the surface pattern. The main weakness I’ve noticed is instruction following. It can occasionally drift between prose turns where DeepSeek and GLM stay tighter. And this is why the 256GB M5 Ultra conversation gets interesting. If Apple can pair that huge unified-memory pool with enough bandwidth, this model class becomes genuinely practical for long-running local agents. We’re talking about frontier-class reasoning on hardware sitting on a desk.

FHILY👑

20,253 görüntüleme • 2 ay önce

Got DeepSeek V4 Flash running on 2x H200s at 160–200 tok/s on JarvisLabsAI this speed is perfect for in the loop things I do with these agents. It feels like a GLM-5.2-class model with much lower hardware requirements. I’m going to daily-drive it for a bit and see how it performs, but first impressions are really good.

Got DeepSeek V4 Flash running on 2x H200s at 160–200 tok/s on JarvisLabsAI this speed is perfect for in the loop things I do with these agents. It feels like a GLM-5.2-class model with much lower hardware requirements. I’m going to daily-drive it for a bit and see how it performs, but first impressions are really good.

Atharva Ingle

21,938 görüntüleme • 3 ay önce

BENCHMARKED: LFM3-1.7B by Liquid AI. Liquid AI published 1.6 GB for the KV cache at 128K context. I ran it on my Mac mini and measured 1.6 GB. The whole model at 128K uses 3.15 GB of GPU memory, under 5% of the 64GB. It still generates 80 tok/s. Only 6 of its 24 layers keep a full KV cache. The other 18 use short convolutions or sliding-window attention. llama.cpp (Metal), Q4_K_M, M5 Pro 64GB, median of 3 runs - 512 ctx: 184 tok/s, 0.09s to first token - 4K ctx: 178 tok/s, 0.72s to first token - 32K ctx: 141 tok/s - 128K ctx: 80 tok/s Q8_0 does 125 tok/s at 512, so 4-bit is 47% faster.

BENCHMARKED: LFM3-1.7B by Liquid AI. Liquid AI published 1.6 GB for the KV cache at 128K context. I ran it on my Mac mini and measured 1.6 GB. The whole model at 128K uses 3.15 GB of GPU memory, under 5% of the 64GB. It still generates 80 tok/s. Only 6 of its 24 layers keep a full KV cache. The other 18 use short convolutions or sliding-window attention. llama.cpp (Metal), Q4_K_M, M5 Pro 64GB, median of 3 runs - 512 ctx: 184 tok/s, 0.09s to first token - 4K ctx: 178 tok/s, 0.72s to first token - 32K ctx: 141 tok/s - 128K ctx: 80 tok/s Q8_0 does 125 tok/s at 512, so 4-bit is 47% faster.

Pratik Gandhi

39,576 görüntüleme • 7 gün önce

vllm-exl3 v0.3.0 is LIVE with custom native CUDA kernels for 2-bit EXL3 on NVIDIA DGX Spark GB10. GLM-5.3-Flash-EXL3-K2 jumped from 16.9 → 24.6 tok/s average single-stream decode, a +45.6% gain. Coding hit 27.6 tok/s, +85.6%. 🚀 The previous ExLlamaV3-backed path inside vLLM was leaving a lot of GB10 bandwidth on the table. So I rewrote the hot path specifically for EXL3 on Blackwell sm_121: → in-register Trellis dequantization → native fused MoE decode → power-of-two chunked prefill GEMM → parallel NVMe pre-warm Then I tested it side-by-side on physical DGX Spark hardware using my GLM-5.3-Flash-EXL3-K2 pack and live vLLM HTTP streaming. 🚀 𝗗𝗘𝗖𝗢𝗗𝗘 𝗧𝗛𝗥𝗢𝗨𝗚𝗛𝗣𝗨𝗧 Single-stream C1: Coding 14.9 → 27.6 tok/s +85.6% Prose 13.7 → 24.6 tok/s +79.3% Reasoning 18.9 → 25.1 tok/s +32.7% Summary 17.1 → 25.6 tok/s +50.0% Format 16.3 → 24.0 tok/s +47.7% Average: 16.9 → 24.6 tok/s 𝗡𝗘𝗧 𝗚𝗔𝗜𝗡: +45.6% ⏱️ 𝗙𝗜𝗥𝗦𝗧-𝗧𝗢𝗞𝗘𝗡 𝗥𝗘𝗦𝗣𝗢𝗡𝗦𝗜𝗩𝗘𝗡𝗘𝗦𝗦 Coding TTFT: 2,344 ms → 859 ms That is a 63.3% reduction, or about 2.7× faster to first token. Follow-up turn with prefix cache hit: 5,608 ms → 3,588 ms 1.56× faster. ⚡ 𝗪𝗛𝗔𝗧 𝗖𝗛𝗔𝗡𝗚𝗘𝗗 𝗢𝗡 𝗧𝗛𝗘 𝗚𝗣𝗨 40 routed-MoE layers: 19.9 ms → 11.5 ms per token Per-layer MoE compute: 497 μs → 287.8 μs That removes 8.4 ms of MoE compute from every generated token. Total per-step wall time: 59.2 ms → 40.6 ms -31.4% The key is `p2b_fused_moe`. Instead of expanding EXL3 weights through a traditional intermediate path, the new kernel performs Trellis dequantization in-register while executing the routed expert computation. The weights stay compressed until the GPU actually needs them. 🔥 𝗣𝗥𝗘𝗙𝗜𝗟𝗟 𝗚𝗢𝗧 𝗔 𝗡𝗔𝗧𝗜𝗩𝗘 𝗣𝗔𝗧𝗛 𝗧𝗢𝗢 The new `exl3_gemm` uses power-of-two chunked prefill GEMM. Measured: 7.85 TFLOPS 13.0× faster than the legacy prefill kernel 1,875 tok/s cold prefill sustained across 65K context 💾 𝗧𝗛𝗘 𝗕𝗢𝗢𝗧 𝗣𝗔𝗧𝗛 𝗡𝗘𝗘𝗗𝗘𝗗 𝗪𝗢𝗥𝗞 𝗧𝗢𝗢 Loading a ~91 GiB model is part of the user experience. Standard shard loading is mostly serial. The updated recipe parallelizes NVMe pre-warm across 8 workers so the storage controller gets used properly instead of feeding a ~100 GiB model one shard at a time. That turns boot-time storage into another optimization target instead of something we simply accept. 💡 𝗧𝗪𝗢 𝗦𝗘𝗥𝗩𝗜𝗡𝗚 𝗙𝗟𝗔𝗚𝗦 𝗪𝗢𝗥𝗧𝗛 𝗞𝗡𝗢𝗪𝗜𝗡𝗚 `--long-prefill-token-threshold 1024` Prevents giant prefill chunks from monopolizing step budgets and starving parallel decode sessions. `--enable-prefix-caching` Avoids paying for the same conversational prefix again on follow-up turns. 📦 𝗘𝗩𝗘𝗥𝗬𝗧𝗛𝗜𝗡𝗚 𝗜𝗦 𝗢𝗣𝗘𝗡 vllm-exl3: GLM-5.3-Flash one-Spark recipe: Model: This is why I like working at the kernel level. The model did not change. The quant did not change. The hardware did not change. The execution path did. 16.9 → 24.6 tok/s. 🛠️ vLLM turboderp

vllm-exl3 v0.3.0 is LIVE with custom native CUDA kernels for 2-bit EXL3 on NVIDIA DGX Spark GB10. GLM-5.3-Flash-EXL3-K2 jumped from 16.9 → 24.6 tok/s average single-stream decode, a +45.6% gain. Coding hit 27.6 tok/s, +85.6%. 🚀 The previous ExLlamaV3-backed path inside vLLM was leaving a lot of GB10 bandwidth on the table. So I rewrote the hot path specifically for EXL3 on Blackwell sm_121: → in-register Trellis dequantization → native fused MoE decode → power-of-two chunked prefill GEMM → parallel NVMe pre-warm Then I tested it side-by-side on physical DGX Spark hardware using my GLM-5.3-Flash-EXL3-K2 pack and live vLLM HTTP streaming. 🚀 𝗗𝗘𝗖𝗢𝗗𝗘 𝗧𝗛𝗥𝗢𝗨𝗚𝗛𝗣𝗨𝗧 Single-stream C1: Coding 14.9 → 27.6 tok/s +85.6% Prose 13.7 → 24.6 tok/s +79.3% Reasoning 18.9 → 25.1 tok/s +32.7% Summary 17.1 → 25.6 tok/s +50.0% Format 16.3 → 24.0 tok/s +47.7% Average: 16.9 → 24.6 tok/s 𝗡𝗘𝗧 𝗚𝗔𝗜𝗡: +45.6% ⏱️ 𝗙𝗜𝗥𝗦𝗧-𝗧𝗢𝗞𝗘𝗡 𝗥𝗘𝗦𝗣𝗢𝗡𝗦𝗜𝗩𝗘𝗡𝗘𝗦𝗦 Coding TTFT: 2,344 ms → 859 ms That is a 63.3% reduction, or about 2.7× faster to first token. Follow-up turn with prefix cache hit: 5,608 ms → 3,588 ms 1.56× faster. ⚡ 𝗪𝗛𝗔𝗧 𝗖𝗛𝗔𝗡𝗚𝗘𝗗 𝗢𝗡 𝗧𝗛𝗘 𝗚𝗣𝗨 40 routed-MoE layers: 19.9 ms → 11.5 ms per token Per-layer MoE compute: 497 μs → 287.8 μs That removes 8.4 ms of MoE compute from every generated token. Total per-step wall time: 59.2 ms → 40.6 ms -31.4% The key is `p2b_fused_moe`. Instead of expanding EXL3 weights through a traditional intermediate path, the new kernel performs Trellis dequantization in-register while executing the routed expert computation. The weights stay compressed until the GPU actually needs them. 🔥 𝗣𝗥𝗘𝗙𝗜𝗟𝗟 𝗚𝗢𝗧 𝗔 𝗡𝗔𝗧𝗜𝗩𝗘 𝗣𝗔𝗧𝗛 𝗧𝗢𝗢 The new `exl3_gemm` uses power-of-two chunked prefill GEMM. Measured: 7.85 TFLOPS 13.0× faster than the legacy prefill kernel 1,875 tok/s cold prefill sustained across 65K context 💾 𝗧𝗛𝗘 𝗕𝗢𝗢𝗧 𝗣𝗔𝗧𝗛 𝗡𝗘𝗘𝗗𝗘𝗗 𝗪𝗢𝗥𝗞 𝗧𝗢𝗢 Loading a ~91 GiB model is part of the user experience. Standard shard loading is mostly serial. The updated recipe parallelizes NVMe pre-warm across 8 workers so the storage controller gets used properly instead of feeding a ~100 GiB model one shard at a time. That turns boot-time storage into another optimization target instead of something we simply accept. 💡 𝗧𝗪𝗢 𝗦𝗘𝗥𝗩𝗜𝗡𝗚 𝗙𝗟𝗔𝗚𝗦 𝗪𝗢𝗥𝗧𝗛 𝗞𝗡𝗢𝗪𝗜𝗡𝗚 `--long-prefill-token-threshold 1024` Prevents giant prefill chunks from monopolizing step budgets and starving parallel decode sessions. `--enable-prefix-caching` Avoids paying for the same conversational prefix again on follow-up turns. 📦 𝗘𝗩𝗘𝗥𝗬𝗧𝗛𝗜𝗡𝗚 𝗜𝗦 𝗢𝗣𝗘𝗡 vllm-exl3: GLM-5.3-Flash one-Spark recipe: Model: This is why I like working at the kernel level. The model did not change. The quant did not change. The hardware did not change. The execution path did. 16.9 → 24.6 tok/s. 🛠️ vLLM turboderp

Cruz

21,720 görüntüleme • 2 ay önce

GLM 5.3 + GLM 5.3 Flash are available for free on Kira AI 😳 Qwen 3.8 Flash is free too new accounts get 150M tokens to use across the free models what you get: - GLM 5.3 Free - GLM 5.3 Flash Free - Qwen 3.8 Flash Free getting started: 1. go to 2. create a new account 3. pick a free model 4. use base url: 5. start testing > third-party proxy > don't send sensitive data 150M free tokens is pretty wild 💀

GLM 5.3 + GLM 5.3 Flash are available for free on Kira AI 😳 Qwen 3.8 Flash is free too new accounts get 150M tokens to use across the free models what you get: - GLM 5.3 Free - GLM 5.3 Flash Free - Qwen 3.8 Flash Free getting started: 1. go to 2. create a new account 3. pick a free model 4. use base url: 5. start testing > third-party proxy > don't send sensitive data 150M free tokens is pretty wild 💀

K2S

22,152 görüntüleme • 1 ay önce

NVIDIA 免费开放这几款模型的访问： - DeepSeek V4.1 Flash - GLM 5.3 - GLM 5.3 Flash - Kimi K3 地址：

NVIDIA 免费开放这几款模型的访问： - DeepSeek V4.1 Flash - GLM 5.3 - GLM 5.3 Flash - Kimi K3 地址：

小樱💞｜实用工具分享

13,454 görüntüleme • 1 ay önce

Claude Fable 5.1 + Opus 5 + GPT-5.6 Sol are FREE 😳 Experiential Labs is giving free access to a huge lineup of AI models what you get: - Claude Fable 5.1 + Fable 5 - Claude Opus 5 + Sonnet 5 - GPT-5.6 Sol + Luna - Gemini 3.7 Flash - Kimi K3 - GLM 5.3 + 5.3 Flash - DeepSeek V4 Flash - Qwen3.8 27B most models have 1M+ context check the full list: free access is live 👀

Claude Fable 5.1 + Opus 5 + GPT-5.6 Sol are FREE 😳 Experiential Labs is giving free access to a huge lineup of AI models what you get: - Claude Fable 5.1 + Fable 5 - Claude Opus 5 + Sonnet 5 - GPT-5.6 Sol + Luna - Gemini 3.7 Flash - Kimi K3 - GLM 5.3 + 5.3 Flash - DeepSeek V4 Flash - Qwen3.8 27B most models have 1M+ context check the full list: free access is live 👀

K2S

25,647 görüntüleme • 1 ay önce

Day-0 Qwen3.8-27B vs Qwen3.6-27B: the voxel pagoda test. Same prompt, one attempt each, single DGX Spark, both NVFP4. 3.8: 75,291 tok · 52m 56s · 23.7 tok/s (vLLM, native MTP) 3.6: 12,117 tok · 5m 13s · 38.8 tok/s (llama.cpp, DFlash K10) 3.8 thought for 160K characters before writing a line of code.

Day-0 Qwen3.8-27B vs Qwen3.6-27B: the voxel pagoda test. Same prompt, one attempt each, single DGX Spark, both NVFP4. 3.8: 75,291 tok · 52m 56s · 23.7 tok/s (vLLM, native MTP) 3.6: 12,117 tok · 5m 13s · 38.8 tok/s (llama.cpp, DFlash K10) 3.8 thought for 160K characters before writing a line of code.

Wësche

102,648 görüntüleme • 2 ay önce

now it's live🔥 GLM-5.2 on RTX 5090s: 80-110 tok/s single stream, up from ~30. 3x faster overnight. come feel it:

now it's live🔥 GLM-5.2 on RTX 5090s: 80-110 tok/s single stream, up from ~30. 3x faster overnight. come feel it:

Ning

157,350 görüntüleme • 3 ay önce