RTX PRO 6000 Blackwell Workstation Edition 96GBBudget pick1792 GB/s (+992)
C
Raises estimated decode speed by about 225%.70.5 tok/s decode
Raises estimated decode speed by about 225%.
~$9,999 MSRP
Qwen3.5 35B A3B needs ~40.2 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M 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
Fit status
Runs well
Decode
21.7 tok/s
TTFT
8908 ms
Safe context
219K
Memory
40.2 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 | C | Runs well | 21.7 tok/s | 4859 ms | 219K |
| Coding | C | Runs well | 21.7 tok/s | 8908 ms | 219K |
| Agentic Coding | C | Runs well | 21.7 tok/s | 12957 ms | 219K |
| Reasoning | C | Runs well | 21.7 tok/s | 10528 ms | 219K |
| RAG | C | Runs well | 21.7 tok/s | 16197 ms | 219K |
Inference speed
Estimated decode speed (tokens/sec) for Qwen3.5 35B A3B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~56 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 | 56.2 | Tight |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 28.1 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 28.1 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 26.1 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 21.7 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 20.6 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 17.7 | Tight |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 16.6 | Heavy offload |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 11.2 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 10.6 | Heavy offload |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 10.3 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 9.7 | Heavy offload |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 6.5 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 2.7 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | 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 Qwen3.5 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 | C40 |
Q3_K_S | 3 | 17.2 GB | Low | C41 |
NVFP4 | 4 | 19.6 GB | Medium | C41 |
Q4_K_M | 4 | 21.3 GB | Medium | C41 |
Q5_K_M | 5 | 25.2 GB | High | C42 |
Q6_K | 6 | 28.7 GB | High | C43 |
Q8_0 | 8 | 37.5 GB | Very High | C45 |
F16Best for your GPU | 16 | 71.8 GB | Maximum | C48 |
Copy-paste commands to run Qwen3.5 35B A3B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "lmstudio-community/Qwen3.5-35B-A3B-GGUF" \
--hf-file "Qwen3.5-35B-A3B-GGUF-Q4_K_M.gguf" \
-c 4096 -ngl 99Upgrade options
RTX PRO 6000 Blackwell Workstation Edition 96GBBudget pickRaises estimated decode speed by about 225%.
~$9,999 MSRP
RTX PRO 6000 Blackwell Server Edition 96GBBest valueRaises estimated decode speed by about 189%.
~$9,999 MSRP
Yes, Mac Studio M2 Ultra 128GB can run Qwen3.5 35B A3B with a C grade (Runs well). Expected decode speed: 21.7 tok/s.
Qwen3.5 35B A3B (35B parameters) requires approximately 40.2 GB of memory with Q4_K_M quantization.
The recommended quantization for Qwen3.5 35B A3B is Q4_K_M, which balances quality and memory efficiency.
On Mac Studio M2 Ultra 128GB, Qwen3.5 35B A3B achieves approximately 21.7 tokens per second decode speed with a time-to-first-token of 8908ms using Q4_K_M quantization.
For coding workloads, Qwen3.5 35B A3B on Mac Studio M2 Ultra 128GB receives a C grade with 21.7 tok/s and 219K context.
On Mac Studio M2 Ultra 128GB, Qwen3.5 35B A3B can safely use up to 219K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
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.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-lmstudio-community--qwen3-5-35b-a3b-gguf-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: