on

Can the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip run Hermes 4 405B?

67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well (tight fit)

Runs well (tight fit). At Q3_K_M it needs about 216 GB of 252 GB usable, with an estimated speed of 27.8 tok/s.

Best quant
Q3_K_M
Generation speed
27.8 tok/s
Prompt processing
142 tok/s
First token (1K prompt)
7.2 s
Largest safe context
75K

Best app to run it on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

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

Open Hermes 4 405B 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

LM Studio

Desktop app · runs on llama.cpp, MLX

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

Open Hermes 4 405B 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? Hermes 4 405B 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 405B

Recommended for the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip: Q3_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 Q3_K_M (UD-Q3_K_XL) files (opens in a new tab)

huggingface.co/unsloth/Hermes-4-405B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Hermes-4-405B-GGUF

Original weights · Hugging Face

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

huggingface.co/NousResearch/Hermes-4-405B (opens in a new tab)

No sign-in needed.

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q3_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 welltight fit
How well it runs on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip: 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.30.2 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.12.5 / 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 score81.7 / 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 GB300 Grace Blackwell Ultra Desktop Superchip

Quant Memory needed Available Speed Runs Quality Download
Q2_K 180 GB 252 GB 35.3 tok/s Runs great 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. GGUF (UD-Q2_K_XL) · folder (opens in a new tab)
Q3_K_M 216 GB 252 GB 27.8 tok/s Runs welltight fit 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. GGUF (UD-Q3_K_XL) · folder (opens in a new tab)
Q4_K_M 265 GB 252 GB 3.3 tok/s Slowoffloads to RAM 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q5_K_M 306 GB 252 GB — Won't run 77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. GGUF (UD-Q5_K_XL) · folder (opens in a new tab)
Q6_K 350 GB 252 GB — Won't run 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q8_0 448 GB 252 GB — Won't run 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
F16 829 GB 252 GB — Won't run 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 10/100 (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

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?