Qwen 3 235B A22B needs ~166.3 GB VRAM. NVIDIA GB200 192GB has 192.0 GB. With Q4_K_M quantization, expect ~137 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
Tight fit
Decode
136.8 tok/s
TTFT
1416 ms
Safe context
131K
Memory
166.3 GB / 192.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Tight fit | 136.8 tok/s | 772 ms | 131K |
| Coding | S | Tight fit | 136.8 tok/s | 1416 ms | 131K |
| Agentic Coding | S | Tight fit | 136.8 tok/s | 2059 ms | 131K |
| Reasoning | S | Tight fit | 136.8 tok/s | 1673 ms | 131K |
| RAG | S | Tight fit | 136.8 tok/s | 2574 ms | 131K |
Inference speed
Estimated decode speed (tokens/sec) for Qwen 3 235B A22B 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 ~11 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 | 11.3 | Tight |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 4.7 | Too big |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 4.4 | Too big |
 RTX 5090 32GB | 32 GB | Q4_K_M | 3.7 | Too big |
2× RX 7900 XTX 24GB | 48 GB | Q4_K_M | 3.6 | Too big |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 3.5 | Too big |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 3.2 | Too big |
| 2× RTX 4090 24GB | 48 GB | Q4_K_M | 2.5 | Too big |
| RTX 4090 24GB | 24 GB | Q4_K_M | 2.3 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 2.2 | Too big |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 2.1 | Too big |
| 2× RTX 3090 24GB | 48 GB | Q4_K_M | 2.1 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 2.0 | Too big |
| RTX 3090 24GB | 24 GB | Q4_K_M | 2.0 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 2.0 | 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 |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 2.0 | Too big |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 2.0 | Too big |
| 4× RTX 3060 12GB | 48 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 235B A22B (235B params) fits at each quantization level on NVIDIA GB200 192GB (192.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 91.7 GB | Low | S85 |
Q3_K_S | 3 | 115.2 GB | Low | S86 |
NVFP4 | 4 | 131.6 GB | Medium | S86 |
Q4_K_MBest for your GPU | 4 | 143.4 GB | Medium | S86 |
Q5_K_M | 5 | 169.2 GB | High | F0 |
Q6_K | 6 | 192.7 GB | High | F0 |
Q8_0 | 8 | 251.5 GB | Very High | F0 |
F16 | 16 | 481.7 GB | Maximum | F0 |
Copy-paste commands to run Qwen 3 235B A22B on your machine.
Run
lms load Qwen3-235B-A22B-Instruct-2507 && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 DeepSeek V4 Flash | 284B | S | 144.8 tok/s |
Yes, NVIDIA GB200 192GB can run Qwen 3 235B A22B with a S grade (Tight fit). Expected decode speed: 136.8 tok/s.
Qwen 3 235B A22B (235B parameters) requires approximately 166.3 GB of memory with Q4_K_M quantization.
The recommended quantization for Qwen 3 235B A22B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA GB200 192GB, Qwen 3 235B A22B achieves approximately 136.8 tokens per second decode speed with a time-to-first-token of 1416ms using Q4_K_M quantization.
For coding workloads, Qwen 3 235B A22B on NVIDIA GB200 192GB receives a S grade with 136.8 tok/s and 131K context.
On NVIDIA GB200 192GB, Qwen 3 235B A22B can safely use up to 131K tokens of context. The model's official context limit is 131K, 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-3-235b-a22b-on-gb200-192gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: