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.

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

antirez

77,759 subscribers

318,484 views • 1 month 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

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 • 2 months 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

293,227 views • 26 days ago

~ 6.5 - 6.7 t/s for GLM 5.1 on M5 Max 128GB Added “Dense” model export, now model load is only 5s ! Experts are streaming from SSD, so we do not pre-load it. Added direct SSD->Slot memory path, removed prefetch... Many dead end experiments. See Export a “dense-only GGUF” and “Fast path ” in tools/flashmob-sidecar/README.md WIP branch for Flash-MoE-SSD

~ 6.5 - 6.7 t/s for GLM 5.1 on M5 Max 128GB Added “Dense” model export, now model load is only 5s ! Experts are streaming from SSD, so we do not pre-load it. Added direct SSD->Slot memory path, removed prefetch... Many dead end experiments. See Export a “dense-only GGUF” and “Fast path ” in tools/flashmob-sidecar/README.md WIP branch for Flash-MoE-SSD

Anemll

29,421 views • 4 months ago

Running a Hermes Agent with GLM 5.2 on a Computer the size of a Deck of Playing Cards 🔥🔥🔥

Running a Hermes Agent with GLM 5.2 on a Computer the size of a Deck of Playing Cards 🔥🔥🔥

Tech2Wild

19,294 views • 1 month ago

made this game with GLM-5.2 (claude code) running on my 32x RTX 4090s

made this game with GLM-5.2 (claude code) running on my 32x RTX 4090s

Ning

26,104 views • 1 month ago

GLM 5.2, open frontier-scale intelligence on Microsoft Foundry with AMD MI300X. Running a Codex goal with an open model never felt this good!

GLM 5.2, open frontier-scale intelligence on Microsoft Foundry with AMD MI300X. Running a Codex goal with an open model never felt this good!

Alvaro Bartolome

27,277 views • 1 month ago

Much better at 17 tokens/sec in M3 Max, fusing a few operations. 128gb m3 max.

Much better at 17 tokens/sec in M3 Max, fusing a few operations. 128gb m3 max.

antirez

25,165 views • 3 months ago

Now video on oMLX + Codex + qwen3.6-35b-a3b 6bit on an M5 Max 128GB. Video normal speed! Command used: onlx launch codex Local AI rocks 💪

Now video on oMLX + Codex + qwen3.6-35b-a3b 6bit on an M5 Max 128GB. Video normal speed! Command used: onlx launch codex Local AI rocks 💪

Ivan Fioravanti ᯅ

11,581 views • 2 months ago

Running GLM-4.7-Flash with OpenCode locally on M4 Max MacBook Pro. 4-bit model runs at 82 tok/sec. Prefill will get ~4x faster with M5 Max MacBook Pro (~28 Jan). EXO will also support disaggregating prefill and decode across devices, e.g. DGX Spark.

Running GLM-4.7-Flash with OpenCode locally on M4 Max MacBook Pro. 4-bit model runs at 82 tok/sec. Prefill will get ~4x faster with M5 Max MacBook Pro (~28 Jan). EXO will also support disaggregating prefill and decode across devices, e.g. DGX Spark.

Alex Cheema

128,404 views • 7 months ago

The first M5 max arrived! Many many thanks to our sponsors ⿻ Audrey Tang 唐鳳 and Niels Gron, the next will arrive on Monday.

The first M5 max arrived! Many many thanks to our sponsors ⿻ Audrey Tang 唐鳳 and Niels Gron, the next will arrive on Monday.

antirez

27,882 views • 3 months ago

First kinda working implementation of GLM 5.2 in DwarfStar. Will take some time to be good enough, but it is a promising start. 433 GB GGUF file. M3 Ultra 512GB.

First kinda working implementation of GLM 5.2 in DwarfStar. Will take some time to be good enough, but it is a promising start. 433 GB GGUF file. M3 Ultra 512GB.

antirez

69,508 views • 2 months ago

DeepSeek v4 PRO running in DwarfStar on a DGX Station. Can go faster, already peaks 50 t/s without DSpark: dynamic VRAM/RAM allocation of experts based on past statistics, 4k t/s prefill on big chunks. VRAM/RAM layer-major streaming. Mixed RAM/VRAM inference requires care.

DeepSeek v4 PRO running in DwarfStar on a DGX Station. Can go faster, already peaks 50 t/s without DSpark: dynamic VRAM/RAM allocation of experts based on past statistics, 4k t/s prefill on big chunks. VRAM/RAM layer-major streaming. Mixed RAM/VRAM inference requires care.

antirez

25,124 views • 5 days 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 • 7 days ago

WIP: First attempt to speed up prefill for Flash-MoE. Original repo did token-by-token without streamed experts. Added: Batched linear attention + batched full attention (Flash Attention style) with custom Metal kernels. Without experts: 6.2x faster prefill (11 -> 68 tok/s) With experts at full-attn layers only: 1.9x faster (11 -> 20.5 tok/s) — same output quality Qwen3.5-397B, 4-bit, 209GB, M5 Max 128GB 1/3

WIP: First attempt to speed up prefill for Flash-MoE. Original repo did token-by-token without streamed experts. Added: Batched linear attention + batched full attention (Flash Attention style) with custom Metal kernels. Without experts: 6.2x faster prefill (11 -> 68 tok/s) With experts at full-attn layers only: 1.9x faster (11 -> 20.5 tok/s) — same output quality Qwen3.5-397B, 4-bit, 209GB, M5 Max 128GB 1/3

Anemll

19,572 views • 5 months ago

Video on LM Studio MLX v.1.8.5 + Codex + qwen3.6-35b-a3b 6bit on an M5 Max 128GB. Video is in normal speed to give you an idea of the experience. Command used: codex --oss -m qwen/qwen3.6-35b-a3b Local AI is becoming powerful 💪

Video on LM Studio MLX v.1.8.5 + Codex + qwen3.6-35b-a3b 6bit on an M5 Max 128GB. Video is in normal speed to give you an idea of the experience. Command used: codex --oss -m qwen/qwen3.6-35b-a3b Local AI is becoming powerful 💪

Ivan Fioravanti ᯅ

40,565 views • 2 months ago

Timelapse #156 (36 hrs) - Worked with the tiny corp on getting GLM 5.2 running on 8xMI300X (sglang won here) - Launched KernelBench-Mega and updated Kernelbench-Hard with h100 and b200 sweeps - Took care of boring business stuff - Did some training sweeps for specialized technical vocab audio model - Some bugs with putting kernelbench-mega and hard on cloud instances so had to do some reruns. Learned a lot though - Setting up my own local rl infra and profiling concurrency 128 rollouts with vllm. Became clear to me that I need to serve in nvfp4, use MoE only for throughput, reap so training doesn’t OOM, dig into the vllm kernel graph itself to not underutilize my hardware from poor flashinfer/cutlass selections for my rtx pro 6000 sm120 architecture - Might do online distillation from glm 5.2 but for now taking it one step at a time - Slept for a bit then woke up and showered - Fixed an issue with SGLang tensor parallel deadlock on GLM 5.2 architecture with MTP enabled - GLM 5.2 inference is 2-3x faster than coding plans and running on amd boxes - Spent time with family - Hung out with some friends - Recorded some yoctogpt lectures with the revamped notebook (high taste btw) - Setting up dflash training for GLM 5.2

Timelapse #156 (36 hrs) - Worked with the tiny corp on getting GLM 5.2 running on 8xMI300X (sglang won here) - Launched KernelBench-Mega and updated Kernelbench-Hard with h100 and b200 sweeps - Took care of boring business stuff - Did some training sweeps for specialized technical vocab audio model - Some bugs with putting kernelbench-mega and hard on cloud instances so had to do some reruns. Learned a lot though - Setting up my own local rl infra and profiling concurrency 128 rollouts with vllm. Became clear to me that I need to serve in nvfp4, use MoE only for throughput, reap so training doesn’t OOM, dig into the vllm kernel graph itself to not underutilize my hardware from poor flashinfer/cutlass selections for my rtx pro 6000 sm120 architecture - Might do online distillation from glm 5.2 but for now taking it one step at a time - Slept for a bit then woke up and showered - Fixed an issue with SGLang tensor parallel deadlock on GLM 5.2 architecture with MTP enabled - GLM 5.2 inference is 2-3x faster than coding plans and running on amd boxes - Spent time with family - Hung out with some friends - Recorded some yoctogpt lectures with the revamped notebook (high taste btw) - Setting up dflash training for GLM 5.2

Elliot Arledge

45,447 views • 2 months ago

Llama 3.3 70B 4-bit running on a 128GB M4 Max with MLX LM (~12 toks/sec) with mactop on the right. "Good enough", local, private and open models are now more accessible than ever!

Llama 3.3 70B 4-bit running on a 128GB M4 Max with MLX LM (~12 toks/sec) with mactop on the right. "Good enough", local, private and open models are now more accessible than ever!

Ivan Fioravanti ᯅ

43,937 views • 1 year ago

Running GLM 4.7 Flash (8-bit) with Tensor Parallel / RDMA on 2 M4 Pro Mac Minis at 60 tok/sec. mlx-lm 0.30.5 features huge speedups for GLM 4.7 Flash for long context (h/t N8 Programs & Awni Hannun). M5 Pro (~28 Jan) will have ~4x faster prefill and ~1.3x faster decode.

Running GLM 4.7 Flash (8-bit) with Tensor Parallel / RDMA on 2 M4 Pro Mac Minis at 60 tok/sec. mlx-lm 0.30.5 features huge speedups for GLM 4.7 Flash for long context (h/t N8 Programs & Awni Hannun). M5 Pro (~28 Jan) will have ~4x faster prefill and ~1.3x faster decode.

Alex Cheema

56,555 views • 6 months ago

"YE3" - pretty heavy scene running real-time on my base M4 Pro Macbook. These things are beasts for 3D work already. Imagine an M5 Max + 128 GB… new era for 3D graphics? Apple

"YE3" - pretty heavy scene running real-time on my base M4 Pro Macbook. These things are beasts for 3D work already. Imagine an M5 Max + 128 GB… new era for 3D graphics? Apple

Marcel Deneuve

17,119 views • 5 months ago

GLM-5.2 8bit running on two M3 Ultra 512GB with MLX distributed? Here it is! 🚀 Decode speed: 17.9 tokens/sec 🔥 Memory used: ~ 760GB 👀 Again keep in mind it's a preliminary PR by super Pedro Cuenca still a WIP!

GLM-5.2 8bit running on two M3 Ultra 512GB with MLX distributed? Here it is! 🚀 Decode speed: 17.9 tokens/sec 🔥 Memory used: ~ 760GB 👀 Again keep in mind it's a preliminary PR by super Pedro Cuenca still a WIP!

Ivan Fioravanti ᯅ

34,175 views • 2 months ago