Can DiffusionGemma 26B A4B run on RX 7900 XTX 24GB?

YES — With Q3_K_S

A83Great

Estimated from fit model

DiffusionGemma 26B A4B needs ~21.1 GB VRAM. RX 7900 XTX 24GB has 24.0 GB. With Q3_K_S quantization, expect ~96 tok/s.

Runtime: vLLMCapacity: TightBandwidth: 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.

DiffusionGemma 26B A4B at Q4_K_M needs 24.2 GB — too much for RX 7900 XTX 24GB (24.0 GB). Runs at Q3_K_S (21.1 GB) with low quality. 2 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 24.2 GB, exceeds 24.0 GB available

24.2 GB required24.0 GB available

101% VRAM needed

0.2 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

60.9 tok/s

TTFT

3178 ms

Safe context

15K

Memory

24.2 GB / 24.0 GB

Memory breakdown

Weights15.7 GB

KV Cache3.7 GB

Runtime2.4 GB

Headroom2.4 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsDiffusionGemma 26B A4B on RX 7900 XTX 24GB
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: 60.9 tok/s decode · 3.2s TTFT (warm) · 152 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	Tight fit	82.7 tok/s	1278 ms	15K
Coding	F	Too heavy	60.9 tok/s	3178 ms	15K
Agentic Coding	F	Too heavy	45.3 tok/s	6219 ms	15K
Reasoning	F	Too heavy	60.9 tok/s	3756 ms	15K
RAG	F	Too heavy	45.3 tok/s	7774 ms	15K

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 RX 7900 XTX 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	10.1 GB	Low	A78
Q3_K_S	3	12.6 GB	Low	A79
NVFP4	4	14.4 GB	Medium	A79
Q4_K_M	4	15.7 GB	Medium	A78
Q5_K_MBest for your GPU	5	18.6 GB	High	A78
Q6_K	6	21.2 GB	High	F0
Q8_0	8	27.6 GB	Very High	F0
F16	16	52.9 GB	Maximum	F0

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

Opciones de mejora

Hardware que ejecuta bien DiffusionGemma 26B A4B

Radeon AI PRO R9700 32GBOpción económica

32 GB VRAM (+8)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.45.2 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Añade margen de memoria para más contexto y para que el modelo envejezca mejor.

~$1,899 MSRP

Radeon Pro W6800 32GBMejor relación calidad-precio

32 GB VRAM (+8)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.34.3 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Añade margen de memoria para más contexto y para que el modelo envejezca mejor.

~$2,249 MSRP

Radeon Pro W7800 32GBMejora AMD

32 GB VRAM (+8)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.40.6 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Añade margen de memoria para más contexto y para que el modelo envejezca mejor.

~$2,499 MSRP

Frequently asked questions

Can RX 7900 XTX 24GB run DiffusionGemma 26B A4B?

Yes, RX 7900 XTX 24GB can run DiffusionGemma 26B A4B at Q3_K_S quantization (Tight fit). The recommended Q4_K_M requires 24.2 GB which exceeds available memory, but at Q3_K_S it needs only 21.1 GB. Expected decode speed: 95.7 tok/s.

How much VRAM does DiffusionGemma 26B A4B need?

DiffusionGemma 26B A4B (25.799999237060547B parameters) requires approximately 24.2 GB at Q4_K_M quantization. On RX 7900 XTX 24GB, it fits at Q3_K_S using 21.1 GB.

What is the best quantization for DiffusionGemma 26B A4B?

The recommended quantization is Q4_K_M, but on RX 7900 XTX 24GB the best fitting quantization is Q3_K_S, which uses 21.1 GB.

What speed will DiffusionGemma 26B A4B run at on RX 7900 XTX 24GB?

On RX 7900 XTX 24GB, DiffusionGemma 26B A4B achieves approximately 95.7 tokens per second decode speed with a time-to-first-token of 2023ms using Q3_K_S quantization.

Can RX 7900 XTX 24GB run DiffusionGemma 26B A4B for coding?

For coding workloads, DiffusionGemma 26B A4B on RX 7900 XTX 24GB receives a F grade with 60.9 tok/s and 15K context.

What context window can DiffusionGemma 26B A4B use on RX 7900 XTX 24GB?

On RX 7900 XTX 24GB, DiffusionGemma 26B A4B can safely use up to 29K tokens of context at Q3_K_S quantization. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for RX 7900 XTX 24GB 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-rx-7900-xtx-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: