Qwen 3.6 35B A3B needs ~41.1 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~59 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
59.0 tok/s
TTFT
3283 ms
Safe context
215K
Memory
41.1 GB / 92.2 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 | S | Runs well | 59.0 tok/s | 1791 ms | 215K |
| Coding | S | Runs well | 59.0 tok/s | 3283 ms | 215K |
| Agentic Coding | S | Runs well | 59.0 tok/s | 4776 ms | 215K |
| Reasoning | S | Runs well | 59.0 tok/s | 3880 ms | 215K |
| RAG | S | Runs well | 59.0 tok/s | 5970 ms | 215K |
How Qwen 3.6 35B A3B (35B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.7 GB | Low | A82 |
Q3_K_S | 3 | 17.2 GB | Low | A83 |
NVFP4 | 4 |
Copy-paste commands to run Qwen 3.6 35B A3B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "Qwen/Qwen3.6-35B-A3B" \
--hf-file "Qwen3.6-35B-A3B-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 123B | S | 5.8 tok/s | ||
| 122B | S |
Yes, Mac Studio M2 Ultra 128GB can run Qwen 3.6 35B A3B with a S grade (Runs well). Expected decode speed: 59.0 tok/s.
Qwen 3.6 35B A3B (35B parameters) requires approximately 41.1 GB of memory with Q4_K_M quantization.
The recommended quantization for Qwen 3.6 35B A3B is Q4_K_M, which balances quality and memory efficiency.
On Mac Studio M2 Ultra 128GB, Qwen 3.6 35B A3B achieves approximately 59.0 tokens per second decode speed with a time-to-first-token of 3283ms using Q4_K_M quantization.
For coding workloads, Qwen 3.6 35B A3B on Mac Studio M2 Ultra 128GB receives a S grade with 59.0 tok/s and 215K context.
On Mac Studio M2 Ultra 128GB, Qwen 3.6 35B A3B can safely use up to 215K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/qwen-3.6-35b-a3b-on-m2-ultra-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
19.6 GB |
| Medium |
| A83 |
Q4_K_M | 4 | 21.3 GB | Medium | A83 |
Q5_K_M | 5 | 25.2 GB | High | A84 |
Q6_K | 6 | 28.7 GB | High | A85 |
Q8_0 | 8 | 37.5 GB | Very High | S87 |
F16Best for your GPU | 16 | 71.8 GB | Maximum | S90 |
| 16.9 tok/s |
Not always. Mac Studio M2 Ultra 128GB 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.