DiffusionGemma 26B A4B needs ~19.6 GB VRAM. MacBook Pro M2 Pro 32GB has 23.0 GB. With Q2_K quantization, expect ~22 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
2.3 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
13.4 tok/s
TTFT
14410 ms
Safe context
6K
Memory
25.3 GB / 23.0 GB
Offload
10%
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 | F | Too heavy | 14.9 tok/s | 7080 ms | 6K |
| Coding | F | Too heavy | 13.4 tok/s | 14410 ms | 6K |
| Agentic Coding | F | Too heavy | 11.1 tok/s | 25301 ms | 6K |
| Reasoning | F | Too heavy | 13.4 tok/s | 17031 ms | 6K |
| RAG | F | Too heavy | 11.1 tok/s | 31627 ms | 6K |
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 M2 Pro 32GB (23.0 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_MBest for your GPU | 4 | 15.7 GB | Medium | A78 |
Q5_K_M | 5 | 18.6 GB | High | F0 |
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 99Opções de upgrade
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$1,099 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$1,599 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$2,499 MSRP
Yes, MacBook Pro M2 Pro 32GB can run DiffusionGemma 26B A4B at Q2_K quantization (Tight fit). The recommended Q4_K_M requires 25.3 GB which exceeds available memory, but at Q2_K it needs only 19.6 GB. Expected decode speed: 22.3 tok/s.
DiffusionGemma 26B A4B (25.799999237060547B parameters) requires approximately 25.3 GB at Q4_K_M quantization. On MacBook Pro M2 Pro 32GB, it fits at Q2_K using 19.6 GB.
The recommended quantization is Q4_K_M, but on MacBook Pro M2 Pro 32GB the best fitting quantization is Q2_K, which uses 19.6 GB.
On MacBook Pro M2 Pro 32GB, DiffusionGemma 26B A4B achieves approximately 22.3 tokens per second decode speed with a time-to-first-token of 8698ms using Q2_K quantization.
For coding workloads, DiffusionGemma 26B A4B on MacBook Pro M2 Pro 32GB receives a F grade with 13.4 tok/s and 6K context.
On MacBook Pro M2 Pro 32GB, DiffusionGemma 26B A4B can safely use up to 31K tokens of context at Q2_K quantization. The model's official context limit is 262K, but available memory constrains the safe maximum.
Not always. MacBook Pro M2 Pro 32GB 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-pro-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: