DiffusionGemma 26B A4B needs ~24.4 GB VRAM. MacBook Pro M3 Pro 36GB has 25.9 GB. With NVFP4 quantization, expect ~15 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
Too heavy
Decode
13.1 tok/s
TTFT
14785 ms
Safe context
17K
Memory
25.7 GB / 25.9 GB
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
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.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Tight fit | 13.1 tok/s | 8065 ms | 17K |
| Coding | F | Too heavy | 13.1 tok/s | 14785 ms | 17K |
| Agentic Coding | F | Too heavy | 10.0 tok/s | 28035 ms | 17K |
| Reasoning | F | Too heavy | 13.1 tok/s | 17474 ms | 17K |
| RAG | F | Too heavy | 10.0 tok/s | 35044 ms | 17K |
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 MacBook Pro M3 Pro 36GB (25.9 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 10.1 GB | Low | A77 |
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 |
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升级选项
Makes the model fit on the accelerator instead of staying completely out of reach.
Adds memory headroom for longer context windows and future model growth.
~$1,099 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Raises estimated decode speed by about 92%.
~$1,599 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Raises estimated decode speed by about 214%.
~$2,499 MSRP
Yes, MacBook Pro M3 Pro 36GB can run DiffusionGemma 26B A4B at NVFP4 quantization (Tight fit). The recommended Q4_K_M requires 25.7 GB which exceeds available memory, but at NVFP4 it needs only 24.4 GB. Expected decode speed: 15.0 tok/s.
DiffusionGemma 26B A4B (25.799999237060547B parameters) requires approximately 25.7 GB at Q4_K_M quantization. On MacBook Pro M3 Pro 36GB, it fits at NVFP4 using 24.4 GB.
The recommended quantization is Q4_K_M, but on MacBook Pro M3 Pro 36GB the best fitting quantization is NVFP4, which uses 24.4 GB.
On MacBook Pro M3 Pro 36GB, DiffusionGemma 26B A4B achieves approximately 15.0 tokens per second decode speed with a time-to-first-token of 12927ms using NVFP4 quantization.
For coding workloads, DiffusionGemma 26B A4B on MacBook Pro M3 Pro 36GB receives a F grade with 13.1 tok/s and 17K context.
On MacBook Pro M3 Pro 36GB, DiffusionGemma 26B A4B can safely use up to 23K tokens of context at NVFP4 quantization. The model's official context limit is 262K, but available memory constrains the safe maximum.
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Not always. MacBook Pro M3 Pro 36GB 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-m3-pro-36gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: