Raises estimated decode speed by about 147%.
Adds memory headroom for longer context windows and future model growth.
~$10,000 MSRP
Codestral 22B needs ~20.0 GB VRAM. AMD Instinct MI60 32GB has 32.0 GB. With Q4_K_M quantization, expect ~37 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
Runs well
Decode
40.2 tok/s
TTFT
4817 ms
Safe context
33K
Memory
20.0 GB / 32.0 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 | B | Runs well | 37.4 tok/s | 2824 ms | 33K |
| Coding | B | Runs well | 37.4 tok/s | 5178 ms | 33K |
| Agentic Coding | B | Runs well | 37.4 tok/s | 7532 ms | 33K |
| Reasoning | B | Runs well | 37.4 tok/s | 6119 ms | 33K |
| RAG | B | Runs well | 37.4 tok/s | 9415 ms | 33K |
How Codestral 22B (22B params) fits at each quantization level on AMD Instinct MI60 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | B55 |
Q3_K_S | 3 | 10.8 GB | Low | B56 |
NVFP4 | 4 |
Copy-paste commands to run Codestral 22B on your machine.
Run
ollama run codestralUpgrade options
Yes, AMD Instinct MI60 32GB can run Codestral 22B with a B grade (Runs well). Expected decode speed: 37.4 tok/s.
Codestral 22B (22B parameters) requires approximately 20.0 GB of memory with Q4_K_M quantization.
The recommended quantization for Codestral 22B is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI60 32GB, Codestral 22B achieves approximately 37.4 tokens per second decode speed with a time-to-first-token of 5178ms using Q4_K_M quantization.
For coding workloads, Codestral 22B on AMD Instinct MI60 32GB receives a B grade with 37.4 tok/s and 33K context.
On AMD Instinct MI60 32GB, Codestral 22B can safely use up to 33K tokens of context. The model's official context limit is 33K, 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/codestral-22b-on-instinct-mi60-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| Medium |
| B57 |
Q4_K_M | 4 | 13.4 GB | Medium | B58 |
Q5_K_M | 5 | 15.8 GB | High | B59 |
Q6_K | 6 | 18.0 GB | High | B59 |
Q8_0Best for your GPU | 8 | 23.5 GB | Very High | B59 |
F16 | 16 | 45.1 GB | Maximum | F0 |