Codestral 2 25.08 needs ~18.8 GB VRAM. RX 7900 XT 20GB has 20.0 GB. With Q4_K_M quantization, expect ~36 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
Tight fit
Decode
36.1 tok/s
TTFT
5356 ms
Safe context
24K
Memory
18.8 GB / 20.0 GB
This setup is broadly balanced for this model.
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.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Tight fit | 36.1 tok/s | 2922 ms | 24K |
| Coding | S | Tight fit | 36.1 tok/s | 5356 ms | 24K |
| Agentic Coding | A | Runs with offload (needs ~0.8 GB host RAM) | 24.0 tok/s | 11747 ms | 24K |
| Reasoning | S | Tight fit | 36.1 tok/s | 6330 ms | 24K |
| RAG | A | Runs with offload (needs ~0.8 GB host RAM) | 24.0 tok/s | 14684 ms |
How Codestral 2 25.08 (22B params) fits at each quantization level on RX 7900 XT 20GB (20.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | A84 |
Q3_K_S | 3 | 10.8 GB | Low | A85 |
NVFP4 | 4 |
Copy-paste commands to run Codestral 2 25.08 on your machine.
Run
lms load codestral-2508 && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 30.5B | A | 40.7 tok/s | ||
| 27B | A | 18.3 tok/s |
Yes, RX 7900 XT 20GB can run Codestral 2 25.08 with a S grade (Tight fit). Expected decode speed: 36.1 tok/s.
Codestral 2 25.08 (22B parameters) requires approximately 18.8 GB of memory with Q4_K_M quantization.
The recommended quantization for Codestral 2 25.08 is Q4_K_M, which balances quality and memory efficiency.
On RX 7900 XT 20GB, Codestral 2 25.08 achieves approximately 36.1 tokens per second decode speed with a time-to-first-token of 5356ms using Q4_K_M quantization.
For coding workloads, Codestral 2 25.08 on RX 7900 XT 20GB receives a S grade with 36.1 tok/s and 24K context.
On RX 7900 XT 20GB, Codestral 2 25.08 can safely use up to 24K tokens of context. The model's official context limit is 256K, 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-2-25.08-on-rx-7900-xt-20gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| 24K |
12.3 GB |
| Medium |
| A85 |
Q4_K_MBest for your GPU | 4 | 13.4 GB | Medium | A84 |
Q5_K_M | 5 | 15.8 GB | High | F0 |
Q6_K | 6 | 18.0 GB | High | F0 |
Q8_0 | 8 | 23.5 GB | Very High | F0 |
F16 | 16 | 45.1 GB | Maximum | F0 |
| 27B | S | 17.3 tok/s |
| 30B | A | 43.3 tok/s |
| 24B | S | 35.2 tok/s |
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.