Nous Hermes 2 Mixtral 8x7B DPO on NVIDIA H100 NVL

Can the NVIDIA H100 NVL run Nous Hermes 2 Mixtral 8x7B DPO?

Yes, it runs great

Runs great. At Q8_0 it needs about 55.9 GB of 94.0 GB usable, with an estimated speed of 110 tok/s.

Best quant: Q8_0
Generation speed: 110 tok/s
Prompt processing: 6,698 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 32K

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 NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO

Ollama One command with Ollama’s own build of this model.
LM Studio Point-and-click: search, download and chat in one window.

On Windows

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run nous-hermes2-mixtral:8x7b-dpo-q8_0

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

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 Nous Hermes 2 Mixtral 8x7B DPO

Recommended for the NVIDIA H100 NVL: Q8_0. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run nous-hermes2-mixtral:8x7b-dpo-q8_0

Quantized files · GGUF

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

Download the Q8_0 file (opens in a new tab)

huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF (opens in a new tab)

ollama run hf.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q8_0

Original weights · Hugging Face

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

huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO (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 52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8_0, 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.	23.4 / 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.	13.7 / 15
Match score	77.1 / 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`	25.1 GB	94.0 GB	210 tok/s	Runs great	36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	29.3 GB	94.0 GB	188 tok/s	Runs great	43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	34.9 GB	94.0 GB	165 tok/s	Runs great	49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	39.5 GB	94.0 GB	148 tok/s	Runs great	50Fair quality (C) · 50 of 100: how capable the model is at Q5_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)
`Q6_K`	44.7 GB	94.0 GB	133 tok/s	Runs great	51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	55.9 GB	94.0 GB	110 tok/s	Runs great	52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	99.8 GB	94.0 GB	17.6 tok/s	Runs welloffloads to RAM	52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (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.

Other hardware that runs it

49Fair quality (C) · 49 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. Apple M4 Max (64 GB) Q4_K_M · 38.9 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q8_0 · 65.3 tok/s · Runs great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q4_K_M · 108 tok/s · Runs well (tight fit)
49Fair quality (C) · 49 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. Apple M1 Max (64 GB) Q4_K_M · 29.5 tok/s · Runs well
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (48 GB) Q4_K_M · 20.8 tok/s · Runs well (tight fit)
51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q6_K · 39.1 tok/s · Runs great

Quick answers

How much memory does Nous Hermes 2 Mixtral 8x7B DPO need on the NVIDIA H100 NVL 94GB?

At Q8_0 it needs about 55.9 GB. The NVIDIA H100 NVL 94GB has 94.0 GB usable.

How fast is Nous Hermes 2 Mixtral 8x7B DPO on the NVIDIA H100 NVL 94GB?

About 110 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Nous Hermes 2 Mixtral 8x7B DPO should I use on the NVIDIA H100 NVL 94GB?

Q8_0. 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.