Check my GPU

on

Can the AMD Radeon PRO W7800 48GB run Hermes 4 70B?

77 ptsGreat (A) · 77 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 15.0/15

Yes, it runs well

Runs well. At Q3_K_M it needs about 40.3 GB of 48.0 GB usable, with an estimated speed of 16.7 tok/s.

Best quant
Q3_K_M
Generation speed
16.7 tok/s
Prompt processing
794 tok/s
First token (1K prompt)
1.3 s
Largest safe context
31K

Download Hermes 4 70B

Recommended for the AMD Radeon PRO W7800 48GB: 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 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:Q3_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 6 days ago against Hugging Face, Ollama and GitHub.

How the A grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.28.0 / 45
Memory fitFull marks when everything sits in GPU or unified 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.9.7 / 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
Total77.7 / 10077 ptsGreat (A) · 77 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the AMD Radeon PRO W7800 48GB

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 33.9 GB 48.0 GB 21.3 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 23.3/45, Memory fit 25.0/25, Speed 10.9/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q3_K_M 40.3 GB 48.0 GB 16.7 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q4_K_M 48.7 GB 48.0 GB 11.1 tok/s Runs with offload 64 ptsGood (B) · 64 of 100 points: Model quality 31.6/45, Memory fit 10.0/25, Speed 7.9/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q5_K_M 55.8 GB 48.0 GB 4.1 tok/s Runs with offload 62 ptsGood (B) · 62 of 100 points: Model quality 32.3/45, Memory fit 10.0/25, Speed 4.8/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q6_K 63.5 GB 48.0 GB 2.4 tok/s Runs with offload 61 ptsGood (B) · 61 of 100 points: Model quality 33.0/45, Memory fit 10.0/25, Speed 3.7/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q8_0 80.5 GB 48.0 GB — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 10.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · folder (opens in a new tab)
F16 147 GB 48.0 GB — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 10.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 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.