DeepSeek V4 Pro (April 2026) on NVIDIA H100 NVL

Can the NVIDIA H100 NVL run DeepSeek V4 Pro (April 2026)?

No, it doesn’t fit

No. DeepSeek V4 Pro (April 2026) needs about 645 GB even at Q2_K; the NVIDIA H100 NVL has 94.0 GB usable.

Download DeepSeek V4 Pro (April 2026)

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/DeepSeek-V4-Pro (opens in a new tab)

No sign-in needed.

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_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 Won't run: 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.	9.0 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Match score	9.0 / 100

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

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

Every quantization on the NVIDIA H100 NVL

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	645 GB	94.0 GB	—	Won't run	66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q3_K_M`	789 GB	94.0 GB	—	Won't run	79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q4_K_M`	981 GB	94.0 GB	—	Won't run	90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	1,141 GB	94.0 GB	—	Won't run	92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	1,317 GB	94.0 GB	—	Won't run	94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	1,701 GB	94.0 GB	—	Won't run	95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	3,203 GB	94.0 GB	—	Won't run	95Excellent quality (A+) · 95 of 100: how capable the model is at F16, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

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

Hardware that can run it

None. No single GPU or device in our catalog runs this model on its own; it needs several GPUs working together.

Models that do run on the NVIDIA H100 NVL

95Excellent quality (A+) · 95 of 100: how capable the model is at F16, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 27B F16 · 40.4 tok/s
94Excellent quality (A+) · 94 of 100: how capable the model is at F16, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27B F16 · 40.4 tok/s
93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3B F16 · 142 tok/s
93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B F16 · 142 tok/s
93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 27B F16 · 40.4 tok/s

Quick answers

How much memory does DeepSeek V4 Pro (April 2026) need on the NVIDIA H100 NVL 94GB?

Even at Q2_K it needs about 645 GB; the NVIDIA H100 NVL 94GB has 94.0 GB usable.

What can the NVIDIA H100 NVL 94GB run instead?

Qwen3.8 27B, Qwen3.6 27B and Qwen3.6 35B-A3B run best on it; the page lists more, each with its speed.

What hardware can run DeepSeek V4 Pro (April 2026)?

No single GPU or device in our catalog runs it on its own; it needs several GPUs working together.

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.