Qwen2.5-Math 72B Instruct on NVIDIA H100 NVL

Can the NVIDIA H100 NVL run Qwen2.5-Math 72B Instruct?

Yes, it runs great

Runs great. At Q6_K it needs about 66.3 GB of 94.0 GB usable, with an estimated speed of 45.7 tok/s.

Best quant: Q6_K
Generation speed: 45.7 tok/s
Prompt processing: 1,188 tok/s
First token (1K prompt): 0.9 s
Largest safe context: 4K

Best app to run it on the NVIDIA H100 NVL

On Linux

vLLM

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

vllm serve Qwen/Qwen2.5-Math-72B-Instruct

LM Studio Point-and-click: search, download and chat in one window.
SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

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

Open Qwen2.5-Math 72B Instruct in LM Studio

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

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 Qwen2.5-Math 72B Instruct

Recommended for the NVIDIA H100 NVL: Q6_K. 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 Q6_K files (opens in a new tab)

huggingface.co/bartowski/Qwen2.5-Math-72B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Qwen2.5-Math-72B-Instruct-GGUF

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct (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 57Good quality (B) · 57 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q6_K, 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.	25.8 / 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 score	80.8 / 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`	35.7 GB	94.0 GB	108 tok/s	Runs great	40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	42.3 GB	94.0 GB	85.1 tok/s	Runs great	48Fair quality (C) · 48 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	51.0 GB	94.0 GB	65.8 tok/s	Runs great	55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	58.3 GB	94.0 GB	54.4 tok/s	Runs great	56Good quality (B) · 56 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q6_K`	66.3 GB	94.0 GB	45.7 tok/s	Runs great	57Good quality (B) · 57 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q8_0`	83.7 GB	94.0 GB	33.5 tok/s	Runs welltight fit	58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`F16`	152 GB	94.0 GB	—	Won't run	58Good quality (B) · 58 of 100: how capable the model is at F16, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 4K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q4_K_M · 30.3 tok/s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q3_K_M · 10.3 tok/s · Runs well (tight fit)
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q4_K_M · 11.6 tok/s · Runs well
48Fair quality (C) · 48 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (128 GB) Q3_K_M · 10.3 tok/s · Runs well
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q4_K_M · 11.9 tok/s · Runs well
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q4_K_M · 11.9 tok/s · Runs well

Quick answers

How much memory does Qwen2.5-Math 72B Instruct need on the NVIDIA H100 NVL 94GB?

At Q6_K it needs about 66.3 GB. The NVIDIA H100 NVL 94GB has 94.0 GB usable.

How fast is Qwen2.5-Math 72B Instruct on the NVIDIA H100 NVL 94GB?

About 45.7 tok/s at Q6_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Qwen2.5-Math 72B Instruct should I use on the NVIDIA H100 NVL 94GB?

Q6_K. 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.