Can the AMD Radeon PRO W7900 run Gemma 4 26B-A4B?

96 pts

Yes, it runs well

Runs well. At Q8_0 it needs about 30.8 GB of 48.0 GB usable, with an estimated speed of 61.2 tok/s.

Best quant: Q8_0
Generation speed: 61.2 tok/s
Prompt processing: 20,003 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

Download Gemma 4 26B-A4B

Recommended for the AMD Radeon PRO W7900: 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.

ollama run gemma4:26b-a4b-it-q8_0

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 Q8_0 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:Q8_0

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 5 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.	41.6 / 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.	14.8 / 15
Total	96.4 / 100	96 ptsExcellent (S) · 96 of 100 points: Model quality 41.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15

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

Every quantization on the AMD Radeon PRO W7900

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	13.7 GB	48.0 GB	197 tok/s	Runs well	75 ptsGreat (A) · 75 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15	GGUF (UD-Q2_K_XL) (opens in a new tab)
`Q3_K_M`	16.0 GB	48.0 GB	155 tok/s	Runs well	82 ptsGreat (A) · 82 of 100 points: Model quality 35.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.7/15	GGUF (opens in a new tab)
`Q4_K_M`	19.1 GB	48.0 GB	120 tok/s	Runs well	88 ptsExcellent (S) · 88 of 100 points: Model quality 39.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.2/15	GGUF (opens in a new tab)
`Q5_K_M`	21.7 GB	48.0 GB	99.3 tok/s	Runs well	90 ptsExcellent (S) · 90 of 100 points: Model quality 40.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.4/15	GGUF (opens in a new tab)
`Q6_K`	24.6 GB	48.0 GB	83.4 tok/s	Runs well	93 ptsExcellent (S) · 93 of 100 points: Model quality 41.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15	GGUF (opens in a new tab)
`Q8_0`	30.8 GB	48.0 GB	61.2 tok/s	Runs well	96 ptsExcellent (S) · 96 of 100 points: Model quality 41.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15	GGUF (opens in a new tab)
`F16`	55.0 GB	48.0 GB	11.8 tok/s	Runs with offload	74 ptsGreat (A) · 74 of 100 points: Model quality 41.6/45, Memory fit 10.0/25, Speed 8.2/15, Memory use 15.0/15	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

96 ptsExcellent (S) · 96 of 100 points: Model quality 41.6/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 15.0/15 Apple M4 Max (64 GB) Q8_0 · 38.7 tok/s
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 NVIDIA GeForce RTX 5090 Q6_K · 201 tok/s
95 ptsExcellent (S) · 95 of 100 points: Model quality 41.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.8/15 NVIDIA RTX PRO 6000 Blackwell F16 · 67.9 tok/s
95 ptsExcellent (S) · 95 of 100 points: Model quality 41.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q6_K · 92.6 tok/s
95 ptsExcellent (S) · 95 of 100 points: Model quality 41.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q6_K · 105 tok/s
95 ptsExcellent (S) · 95 of 100 points: Model quality 41.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q6_K · 113 tok/s

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.