Can DiffusionGemma 26B A4B run on NVIDIA L40S 48GB?

YES — Runs Great

A82Great

Estimated from fit model

DiffusionGemma 26B A4B needs ~26.6 GB VRAM. NVIDIA L40S 48GB has 48.0 GB. With Q4_K_M quantization, expect ~81 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) — 26.6 GB, 80.6 tok/s, Runs well

26.6 GB required48.0 GB available

55% VRAM used

Fit status

Runs well

Decode

80.6 tok/s

TTFT

2402 ms

Safe context

109K

Memory

26.6 GB / 48.0 GB

Memory breakdown

Weights15.7 GB

KV Cache3.7 GB

Runtime2.4 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsDiffusionGemma 26B A4B on NVIDIA L40S 48GB
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: 80.6 tok/s decode · 2.4s TTFT (warm) · 202 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	80.6 tok/s	1310 ms	109K
Coding	A	Runs well	80.6 tok/s	2402 ms	109K
Agentic Coding	A	Runs well	80.6 tok/s	3494 ms	109K
Reasoning	A	Runs well	80.6 tok/s	2839 ms	109K
RAG	A	Runs well	80.6 tok/s	4368 ms	109K

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 NVIDIA L40S 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	10.1 GB	Low	A72
Q3_K_S	3	12.6 GB	Low	A72
NVFP4	4	14.4 GB	Medium	A73
Q4_K_M	4	15.7 GB	Medium	A73
Q5_K_M	5	18.6 GB	High	A74
Q6_K	6	21.2 GB	High	A75
Q8_0Best for your GPU	8	27.6 GB	Very High	A77
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

Your hardware

More models your NVIDIA L40S 48GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	77.4 tok/s
Qwen 3.5 27B	27B	S	35.4 tok/s
Qwen 3.6 27B	27B	S	35.5 tok/s
Qwen 3.6 35B A3B	35B	S	65.1 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	80.1 tok/s

Frequently asked questions

Can NVIDIA L40S 48GB run DiffusionGemma 26B A4B?

Yes, NVIDIA L40S 48GB can run DiffusionGemma 26B A4B with a A grade (Runs well). Expected decode speed: 80.6 tok/s.

How much VRAM does DiffusionGemma 26B A4B need?

DiffusionGemma 26B A4B (25.799999237060547B parameters) requires approximately 26.6 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 NVIDIA L40S 48GB?

On NVIDIA L40S 48GB, DiffusionGemma 26B A4B achieves approximately 80.6 tokens per second decode speed with a time-to-first-token of 2402ms using Q4_K_M quantization.

Can NVIDIA L40S 48GB run DiffusionGemma 26B A4B for coding?

For coding workloads, DiffusionGemma 26B A4B on NVIDIA L40S 48GB receives a A grade with 80.6 tok/s and 109K context.

What context window can DiffusionGemma 26B A4B use on NVIDIA L40S 48GB?

On NVIDIA L40S 48GB, DiffusionGemma 26B A4B can safely use up to 109K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for NVIDIA L40S 48GB 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-l40s-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: