Qwen 3 235B A22B needs ~148.2 GB VRAM. AMD Instinct MI250X 128GB has 128.0 GB. With NVFP4 quantization, expect ~32 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
31.9 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
23.8 tok/s
TTFT
8119 ms
Safe context
4K
Memory
159.9 GB / 128.0 GB
Offload
20%
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 17.9 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 24.3 tok/s | 4346 ms | 4K |
| Coding | F | Too heavy | 23.8 tok/s | 8119 ms | 4K |
| Agentic Coding | F | Too heavy | 23.0 tok/s | 12260 ms | 4K |
| Reasoning | F | Too heavy | 23.8 tok/s | 9596 ms | 4K |
| RAG | F | Too heavy | 23.0 tok/s | 15325 ms | 4K |
How Qwen 3 235B A22B (235B params) fits at each quantization level on AMD Instinct MI250X 128GB (128.0 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 startアップグレードオプション
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
〜$8,000 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
〜$15,000 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
〜$20,000 MSRP
Yes, AMD Instinct MI250X 128GB can run Qwen 3 235B A22B at NVFP4 quantization (Very compromised (needs ~17.9 GB host RAM)). The recommended Q4_K_M requires 159.9 GB which exceeds available memory, but at NVFP4 it needs only 148.2 GB. Expected decode speed: 32.0 tok/s.
Qwen 3 235B A22B (235B parameters) requires approximately 159.9 GB at Q4_K_M quantization. On AMD Instinct MI250X 128GB, it fits at NVFP4 using 148.2 GB.
The recommended quantization is Q4_K_M, but on AMD Instinct MI250X 128GB the best fitting quantization is NVFP4, which uses 148.2 GB.
On AMD Instinct MI250X 128GB, Qwen 3 235B A22B achieves approximately 32.0 tokens per second decode speed with a time-to-first-token of 6045ms using NVFP4 quantization.
For coding workloads, Qwen 3 235B A22B on AMD Instinct MI250X 128GB receives a F grade with 23.8 tok/s and 4K context.
On AMD Instinct MI250X 128GB, Qwen 3 235B A22B can safely use up to 4K tokens of context at NVFP4 quantization. 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-instinct-mi250x-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: