Can Codestral 22B v0.1 i1 run on AMD Instinct MI100 32GB?
YES — Runs Great
Codestral 22B v0.1 i1 needs ~20.1 GB VRAM. AMD Instinct MI100 32GB has 32.0 GB. With Q4_K_M quantization, expect ~60 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
Runs well
Decode
59.5 tok/s
TTFT
3255 ms
Safe context
90K
Memory
20.1 GB / 32.0 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 | C | Runs well | 59.5 tok/s | 1775 ms | 90K |
| Coding | C | Runs well | 59.5 tok/s | 3255 ms | 90K |
| Agentic Coding | C | Runs well | 59.5 tok/s | 4734 ms | 90K |
| Reasoning | C | Runs well | 59.5 tok/s | 3847 ms | 90K |
| RAG | C | Runs well | 59.5 tok/s | 5918 ms | 90K |
Quantization options
How Codestral 22B v0.1 i1 (22B params) fits at each quantization level on AMD Instinct MI100 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | C45 |
Q3_K_S | 3 | 10.8 GB | Low | C46 |
NVFP4 | 4 | 12.3 GB | Medium | C47 |
Q4_K_M | 4 | 13.4 GB | Medium | C47 |
Q5_K_M | 5 | 15.8 GB | High | C48 |
Q6_K | 6 | 18.0 GB | High | C49 |
Q8_0Best for your GPU | 8 | 23.5 GB | Very High | C48 |
F16 | 16 | 45.1 GB | Maximum | F0 |
Get started
Copy-paste commands to run Codestral 22B v0.1 i1 on your machine.
Run
lms load hf-mradermacher--codestral-22b-v0-1-i1-gguf && lms server start