on

Can the NVIDIA H100 NVL run GLM-4.6V?

78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At Q4_K_M it needs about 72.5 GB of 94.0 GB usable, with an estimated speed of 170 tok/s.

Best quant
Q4_K_M
Generation speed
170 tok/s
Prompt processing
7,200 tok/s
First token (1K prompt)
0.3 s
Largest safe context
119K

Best app to run it on the NVIDIA H100 NVL

On Linux

LM Studio

Desktop app · runs on llama.cpp, MLX

  • Point-and-click: search, download and chat in one window.

Open GLM-4.6V in LM Studio

  • llama.cpp Usually the first to support new model architectures.
  • Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

  • Point-and-click: search, download and chat in one window.

Open GLM-4.6V in LM Studio

  • llama.cpp Usually the first to support new model architectures.
  • Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

Want an agent? GLM-4.6V supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download GLM-4.6V

Recommended for the NVIDIA H100 NVL: Q4_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q4_K_M files (opens in a new tab)

huggingface.co/unsloth/GLM-4.6V-GGUF (opens in a new tab)

ollama run hf.co/unsloth/GLM-4.6V-GGUF

Original weights · Hugging Face

Full-precision files from Zhipu AI, for fine-tuning, vLLM, Transformers.

huggingface.co/zai-org/GLM-4.6V (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q4_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great
How well it runs on the NVIDIA H100 NVL: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.35.5 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.15.0 / 15
Match score90.5 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA H100 NVL

Quant Memory needed Available Speed Runs Quality Download
Q2_K 49.9 GB 94.0 GB 215 tok/s Runs great 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q3_K_M 59.6 GB 94.0 GB 193 tok/s Runs great 69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q4_K_M 72.5 GB 94.0 GB 170 tok/s Runs great 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q5_K_M 83.3 GB 94.0 GB 153 tok/s Runs welltight fit 80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q6_K 95.2 GB 94.0 GB 100 tok/s Runs welloffloads to RAM 82Great quality (A) · 82 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q8_0 121 GB 94.0 GB — Won't run 83Great quality (A) · 83 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
F16 222 GB 94.0 GB — Won't run 83Great quality (A) · 83 of 100: how capable the model is at F16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Quick answers

How much memory does GLM-4.6V need on the NVIDIA H100 NVL 94GB?

At Q4_K_M it needs about 72.5 GB. The NVIDIA H100 NVL 94GB has 94.0 GB usable.

How fast is GLM-4.6V on the NVIDIA H100 NVL 94GB?

About 170 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of GLM-4.6V should I use on the NVIDIA H100 NVL 94GB?

Q4_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?