Hermes 4 70B on NVIDIA RTX PRO 6000 Blackwell

Can the NVIDIA RTX PRO 6000 Blackwell run Hermes 4 70B?

Yes, it runs great

Runs great. At Q4_K_M it needs about 51.1 GB of 96.0 GB usable, with an estimated speed of 31.2 tok/s.

Best quant: Q4_K_M
Generation speed: 31.2 tok/s
Prompt processing: 1,276 tok/s
First token (1K prompt): 0.8 s
Largest safe context: 128K

Best app to run it on the NVIDIA RTX PRO 6000 Blackwell

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

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

Open Hermes 4 70B 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 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/Hermes-4-70B

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

Want an agent? Hermes 4 70B 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 Hermes 4 70B

Recommended for the NVIDIA RTX PRO 6000 Blackwell: 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 file (opens in a new tab)

huggingface.co/unsloth/Hermes-4-70B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Hermes-4-70B-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/NousResearch/Hermes-4-70B (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 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (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 RTX PRO 6000 Blackwell: 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.	31.6 / 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.	13.2 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	12.3 / 15
Match score	82.2 / 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 RTX PRO 6000 Blackwell

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	36.3 GB	96.0 GB	51.2 tok/s	Runs great	51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	42.7 GB	96.0 GB	40.3 tok/s	Runs great	62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	51.1 GB	96.0 GB	31.2 tok/s	Runs great	70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	58.2 GB	96.0 GB	25.8 tok/s	Runs well	71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	65.9 GB	96.0 GB	21.6 tok/s	Runs well	73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q8_0`	82.9 GB	96.0 GB	15.9 tok/s	Runs welltight fit	74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`F16`	149 GB	96.0 GB	—	Won't run	74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 9/100 (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

62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q3_K_M · 10.6 tok/s · Runs well (tight fit)
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q4_K_M · 12.0 tok/s · Runs well
70Great quality (A) · 70 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 M3 Ultra (256 GB) Q4_K_M · 12.3 tok/s · Runs well
62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (128 GB) Q3_K_M · 10.6 tok/s · Runs well
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q4_K_M · 12.3 tok/s · Runs well
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q2_K · 25.4 tok/s · Runs well (offloads to RAM)

Quick answers

How much memory does Hermes 4 70B need on the NVIDIA RTX PRO 6000 Blackwell 96GB?

At Q4_K_M it needs about 51.1 GB. The NVIDIA RTX PRO 6000 Blackwell 96GB has 96.0 GB usable.

How fast is Hermes 4 70B on the NVIDIA RTX PRO 6000 Blackwell 96GB?

About 31.2 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Hermes 4 70B should I use on the NVIDIA RTX PRO 6000 Blackwell 96GB?

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.