Check my GPU

on

Can the AMD Radeon PRO W6800 run Gemma 4 26B-A4B?

96 ptsExcellent (S) · 96 of 100 points: Model quality 41.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

Yes, it runs well

Runs well. At Q6_K it needs about 23.8 GB of 32.0 GB usable, with an estimated speed of 49.4 tok/s.

Best quant
Q6_K
Generation speed
49.4 tok/s
Prompt processing
5,825 tok/s
First token (1K prompt)
0.3 s
Largest safe context
171K

Download Gemma 4 26B-A4B

Recommended for the AMD Radeon PRO W6800: Q6_K. 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.

ollama run gemma4:26b

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

Quantized files · GGUF

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

Download the Q6_K file (opens in a new tab)

huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF (opens in a new tab)

ollama run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:Q6_K

Original weights · Hugging Face

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

huggingface.co/google/gemma-4-26B-A4B-it (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Google. The weights themselves download from Hugging Face.

github.com/google-deepmind/gemma (opens in a new tab)

git clone https://github.com/google-deepmind/gemma

Google DeepMind’s official Gemma library.

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

How the S 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.41.2 / 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.15.0 / 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
Total96.2 / 10096 ptsExcellent (S) · 96 of 100 points: Model quality 41.2/45, Memory fit 25.0/25, Speed 15.0/15, 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 W6800

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 12.9 GB 32.0 GB 117 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.3/15 GGUF (UD-Q2_K_XL) (opens in a new tab)
Q3_K_M 15.2 GB 32.0 GB 92.1 tok/s Runs well 85 ptsExcellent (S) · 85 of 100 points: Model quality 35.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15 GGUF (opens in a new tab)
Q4_K_M 18.3 GB 32.0 GB 71.2 tok/s Runs well 92 ptsExcellent (S) · 92 of 100 points: Model quality 39.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.2/15 GGUF (opens in a new tab)
Q5_K_M 20.9 GB 32.0 GB 58.8 tok/s Runs well 95 ptsExcellent (S) · 95 of 100 points: Model quality 40.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q6_K 23.8 GB 32.0 GB 49.4 tok/s Runs well 96 ptsExcellent (S) · 96 of 100 points: Model quality 41.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q8_0 30.0 GB 32.0 GB 36.3 tok/s Tight fit 94 ptsExcellent (S) · 94 of 100 points: Model quality 41.6/45, Memory fit 24.0/25, Speed 14.3/15, Memory use 15.0/15 GGUF (opens in a new tab)
F16 54.2 GB 32.0 GB — Won't run 12 ptsWon't run (F) · 12 of 100 points: Model quality 12.5/45, 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.