DiffusionGemma 26B A4B needs ~28.7 GB VRAM. Mac Studio M2 Ultra 64GB has 46.1 GB. With Q4_K_M quantization, expect ~56 tok/s.
Operating mode
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.
Select quantization to explore
Fit status
Runs well
Decode
55.5 tok/s
TTFT
3489 ms
Safe context
92K
Memory
28.7 GB / 46.1 GB
This setup is broadly balanced for this model.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 55.5 tok/s | 1903 ms | 92K |
| Coding | A | Runs well | 55.5 tok/s | 3489 ms | 92K |
| Agentic Coding | A | Runs well | 55.5 tok/s | 5075 ms | 92K |
| Reasoning | A | Runs well | 55.5 tok/s | 4124 ms | 92K |
| RAG | A | Runs well | 55.5 tok/s | 6344 ms | 92K |
Inference speed
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.
How DiffusionGemma 26B A4B (25.799999237060547B params) fits at each quantization level on Mac Studio M2 Ultra 64GB (46.1 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 10.1 GB | Low | A72 |
Q3_K_S | 3 | 12.6 GB | Low | A73 |
NVFP4 | 4 | 14.4 GB | Medium | A73 |
Q4_K_M | 4 | 15.7 GB | Medium | A74 |
Q5_K_M | 5 | 18.6 GB | High | A75 |
Q6_K | 6 | 21.2 GB | High | A76 |
Q8_0Best for your GPU | 8 | 27.6 GB | Very High | A77 |
F16 | 16 | 52.9 GB | Maximum | F0 |
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 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 53.3 tok/s | |
| Qwen 3.5 27B | 27B | S | 24.3 tok/s | |
| Qwen 3.6 27B | 27B | S | 24.4 tok/s | |
| Qwen 3.6 35B A3B | 35B | S | 44.8 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 55.1 tok/s |
Yes, Mac Studio M2 Ultra 64GB can run DiffusionGemma 26B A4B with a A grade (Runs well). Expected decode speed: 55.5 tok/s.
DiffusionGemma 26B A4B (25.799999237060547B parameters) requires approximately 28.7 GB of memory with Q4_K_M quantization.
The recommended quantization for DiffusionGemma 26B A4B is Q4_K_M, which balances quality and memory efficiency.
On Mac Studio M2 Ultra 64GB, DiffusionGemma 26B A4B achieves approximately 55.5 tokens per second decode speed with a time-to-first-token of 3489ms using Q4_K_M quantization.
For coding workloads, DiffusionGemma 26B A4B on Mac Studio M2 Ultra 64GB receives a A grade with 55.5 tok/s and 92K context.
On Mac Studio M2 Ultra 64GB, DiffusionGemma 26B A4B can safely use up to 92K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.
Not always. Mac Studio M2 Ultra 64GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/diffusiongemma-26b-a4b-on-m2-ultra-64gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: