Qwen 3 235B A22B needs ~161.2 GB VRAM. NVIDIA H200 141GB has 141.0 GB. With Q4_K_M quantization, expect ~56 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
20.2 GB over capacity — needs offload or smaller quantization
Fit status
Very compromised (needs ~18 GB host RAM)
Decode
56.1 tok/s
TTFT
3450 ms
Safe context
4K
Memory
161.2 GB / 141.0 GB
Offload
10%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 18.0 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Very compromised (needs ~16.9 GB host RAM) | 56.9 tok/s | 1855 ms | 4K |
| Coding | A | Very compromised (needs ~18 GB host RAM) | 56.1 tok/s | 3450 ms | 4K |
| Agentic Coding | A | Very compromised (needs ~20.2 GB host RAM) | 54.5 tok/s | 5167 ms | 4K |
| Reasoning | A | Very compromised (needs ~18 GB host RAM) | 56.1 tok/s | 4078 ms | 4K |
| RAG | A | Very compromised (needs ~20.2 GB host RAM) | 54.5 tok/s | 6459 ms | 4K |
How Qwen 3 235B A22B (235B params) fits at each quantization level on NVIDIA H200 141GB (141.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_KBest for your GPU | 2 | 91.7 GB | Low | S86 |
Q3_K_S | 3 | 115.2 GB | Low | F0 |
NVFP4 | 4 | 131.6 GB | Medium | F0 |
Q4_K_M | 4 | 143.4 GB | Medium | F0 |
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 startYes, NVIDIA H200 141GB can run Qwen 3 235B A22B with a A grade (Very compromised (needs ~18 GB host RAM)). Expected decode speed: 56.1 tok/s.
Qwen 3 235B A22B (235B parameters) requires approximately 161.2 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 H200 141GB, Qwen 3 235B A22B achieves approximately 56.1 tokens per second decode speed with a time-to-first-token of 3450ms using Q4_K_M quantization.
For coding workloads, Qwen 3 235B A22B on NVIDIA H200 141GB receives a A grade with 56.1 tok/s and 4K context.
On NVIDIA H200 141GB, Qwen 3 235B A22B can safely use up to 4K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/qwen-3-235b-a22b-on-h200-141gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: