Can DiffusionGemma 26B A4B run on AMD Instinct MI250X 128GB?

YES — Runs Great

A76Great

Estimated from fit model

DiffusionGemma 26B A4B needs ~34.6 GB VRAM. AMD Instinct MI250X 128GB has 128.0 GB. With Q4_K_M quantization, expect ~299 tok/s.

Runtime: vLLMCapacity: RoomyBandwidth: HighStack: OptimizedBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 34.6 GB, 298.5 tok/s, Runs well

34.6 GB required128.0 GB available

27% VRAM used

Fit status

Runs well

Decode

298.5 tok/s

TTFT

649 ms

Safe context

262K

Memory

34.6 GB / 128.0 GB

Memory breakdown

Weights15.7 GB

KV Cache3.7 GB

Runtime2.4 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsDiffusionGemma 26B A4B on AMD Instinct MI250X 128GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.

Given information:
  - Speed = 60 mph (miles per hour)
  - Time  = 2.5 hours

Formula: Distance = Speed x Time

Calculation:
  Distance = 60 mph x 2.5 h
           = 150 miles

The train travels 150 miles.

Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.

Breakdown:
  - First half: 1.25 hours at 60 mph = 75 miles
  - Stop: 20 minutes (no distance)
  - Second half: 1.25 hours at 60 mph = 75 miles

Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph

The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 298.5 tok/s decode · 649ms TTFT (warm) · 746 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	298.5 tok/s	354 ms	262K
Coding	A	Runs well	298.5 tok/s	649 ms	262K
Agentic Coding	A	Runs well	298.5 tok/s	943 ms	262K
Reasoning	A	Runs well	298.5 tok/s	767 ms	262K
RAG	A	Runs well	298.5 tok/s	1179 ms	262K

Inference speed

DiffusionGemma 26B A4B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for DiffusionGemma 26B A4B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~144 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	143.6	Fits
RTX 4090 24GB	24 GB	Q4_K_M	67.5	Too big
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	66.6	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	60.9	Too big
RTX 3090 24GB	24 GB	Q4_K_M	57.7	Too big
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	55.5	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	52.6	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	41.1	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	41.1	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	28.7	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	26.3	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	25.1	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	24.6	Too big
RTX 4070 12GB	12 GB	Q4_K_M	8.6	Too big
RTX 3060 12GB	12 GB	Q4_K_M	5.4	Too big
RTX 4060 8GB	8 GB	Q4_K_M	3.6	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How DiffusionGemma 26B A4B (25.799999237060547B params) fits at each quantization level on AMD Instinct MI250X 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	10.1 GB	Low	B67
Q3_K_S	3	12.6 GB	Low	B67
NVFP4	4	14.4 GB	Medium	B67
Q4_K_M	4	15.7 GB	Medium	B67
Q5_K_M	5	18.6 GB	High	B68
Q6_K	6	21.2 GB	High	B68
Q8_0	8	27.6 GB	Very High	B69
F16Best for your GPU	16	52.9 GB	Maximum	A73

Get started

Copy-paste commands to run DiffusionGemma 26B A4B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "google/diffusiongemma-26B-A4B-it" \
  --hf-file "diffusiongemma-26B-A4B-it-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your AMD Instinct MI250X 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	28.9 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	286.8 tok/s
Qwen 3.5 27B	27B	S	130.9 tok/s
Qwen 3.6 27B	27B	S	131.3 tok/s
Qwen 3.5 122B A10B	122B	S	76.3 tok/s

Frequently asked questions

Can AMD Instinct MI250X 128GB run DiffusionGemma 26B A4B?

Yes, AMD Instinct MI250X 128GB can run DiffusionGemma 26B A4B with a A grade (Runs well). Expected decode speed: 298.5 tok/s.

How much VRAM does DiffusionGemma 26B A4B need?

DiffusionGemma 26B A4B (25.799999237060547B parameters) requires approximately 34.6 GB of memory with Q4_K_M quantization.

What is the best quantization for DiffusionGemma 26B A4B?

The recommended quantization for DiffusionGemma 26B A4B is Q4_K_M, which balances quality and memory efficiency.

What speed will DiffusionGemma 26B A4B run at on AMD Instinct MI250X 128GB?

On AMD Instinct MI250X 128GB, DiffusionGemma 26B A4B achieves approximately 298.5 tokens per second decode speed with a time-to-first-token of 649ms using Q4_K_M quantization.

Can AMD Instinct MI250X 128GB run DiffusionGemma 26B A4B for coding?

For coding workloads, DiffusionGemma 26B A4B on AMD Instinct MI250X 128GB receives a A grade with 298.5 tok/s and 262K context.

What context window can DiffusionGemma 26B A4B use on AMD Instinct MI250X 128GB?

On AMD Instinct MI250X 128GB, DiffusionGemma 26B A4B can safely use up to 262K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI250X 128GB See all hardware for DiffusionGemma 26B A4B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/diffusiongemma-26b-a4b-on-instinct-mi250x-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: