Can Qwen 3 235B A22B run on AMD Instinct MI300X 192GB?
YES — Tight Fit
Qwen 3 235B A22B needs ~166.3 GB VRAM. AMD Instinct MI300X 192GB has 192.0 GB. With Q4_K_M quantization, expect ~84 tok/s.
Operating mode
Choose the run profile you care about
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
84.1 tok/s
TTFT
2301 ms
Safe context
131K
Memory
166.3 GB / 192.0 GB
Memory breakdown
See how fast it feels
What limits this setup
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.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Tight fit | 84.1 tok/s | 1255 ms | 131K |
| Coding | S | Tight fit | 84.1 tok/s | 2301 ms | 131K |
| Agentic Coding | S | Tight fit | 84.1 tok/s | 3347 ms | 131K |
| Reasoning | S | Tight fit | 84.1 tok/s | 2719 ms | 131K |
| RAG | S | Tight fit | 84.1 tok/s | 4184 ms | 131K |
Quantization options
How Qwen 3 235B A22B (235B params) fits at each quantization level on AMD Instinct MI300X 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 |
Get started
Copy-paste commands to run Qwen 3 235B A22B on your machine.
Run
lms load Qwen3-235B-A22B-Instruct-2507 && lms server startYour hardware
More models your AMD Instinct MI300X 192GB can run
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 👁 DeepSeek DeepSeek V4 Flash | 284B | S | 89.1 tok/s |
