Qwen 3.5 122B A10B needs ~105.4 GB VRAM. Mac Studio M3 Ultra 256GB has 184.3 GB. With Q4_K_M quantization, expect ~35 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
34.7 tok/s
TTFT
5579 ms
Safe context
131K
Memory
105.4 GB / 184.3 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 | 34.7 tok/s | 3043 ms | 131K |
| Coding | S | Runs well | 34.7 tok/s | 5579 ms | 131K |
| Agentic Coding | S | Runs well | 34.7 tok/s | 8114 ms | 131K |
| Reasoning | S | Runs well | 34.7 tok/s | 6593 ms | 131K |
| RAG | S | Runs well | 34.7 tok/s | 10143 ms | 131K |
Inference speed
Estimated decode speed (tokens/sec) for Qwen 3.5 122B A10B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~35 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? |
|---|---|---|---|---|
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 34.7 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 28.9 | Offloads |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 27.4 | Offloads |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 21.4 | Offloads |
2× RX 7900 XTX 24GB | 48 GB | Q4_K_M | 11.3 | Too big |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 10.0 | Too big |
 2× RTX 4090 24GB | 48 GB | Q4_K_M | 7.6 | Too big |
| RTX 5090 32GB | 32 GB | Q4_K_M | 7.2 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 7.0 | Too big |
| 2× RTX 3090 24GB | 48 GB | Q4_K_M | 6.5 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 6.4 | Too big |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 5.9 | Too big |
| 4× RTX 3060 12GB | 48 GB | Q4_K_M | 5.7 | Too big |
| RTX 4090 24GB | 24 GB | Q4_K_M | 4.6 | Too big |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 4.2 | Too big |
| RTX 3090 24GB | 24 GB | Q4_K_M | 4.0 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 3.7 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 2.3 | 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 Qwen 3.5 122B A10B (122B params) fits at each quantization level on Mac Studio M3 Ultra 256GB (184.3 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 47.6 GB | Low | A84 |
Q3_K_S | 3 | 59.8 GB | Low | S85 |
NVFP4 | 4 | 68.3 GB | Medium | S86 |
Q4_K_M | 4 | 74.4 GB | Medium | S87 |
Q5_K_M | 5 | 87.8 GB | High | S88 |
Q6_K | 6 | 100.0 GB | High | S90 |
Q8_0Best for your GPU | 8 | 130.5 GB | Very High | S90 |
F16 | 16 | 250.1 GB | Maximum | F0 |
Copy-paste commands to run Qwen 3.5 122B A10B on your machine.
Run
lms load Qwen3.5-122B-A10B-Instruct && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Devstral 2 123B Instruct | 123B | S | 8.1 tok/s |
Yes, Mac Studio M3 Ultra 256GB can run Qwen 3.5 122B A10B with a S grade (Runs well). Expected decode speed: 34.7 tok/s.
Qwen 3.5 122B A10B (122B parameters) requires approximately 105.4 GB of memory with Q4_K_M quantization.
The recommended quantization for Qwen 3.5 122B A10B is Q4_K_M, which balances quality and memory efficiency.
On Mac Studio M3 Ultra 256GB, Qwen 3.5 122B A10B achieves approximately 34.7 tokens per second decode speed with a time-to-first-token of 5579ms using Q4_K_M quantization.
For coding workloads, Qwen 3.5 122B A10B on Mac Studio M3 Ultra 256GB receives a S grade with 34.7 tok/s and 131K context.
On Mac Studio M3 Ultra 256GB, Qwen 3.5 122B A10B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
Not always. Mac Studio M3 Ultra 256GB 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/qwen-3.5-122b-a10b-on-m3-ultra-256gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: