Codestral Mamba 7B needs ~7.3 GB VRAM. RX 6800 16GB has 16.0 GB. With Q4_K_M quantization, expect ~76 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
75.8 tok/s
TTFT
2553 ms
Safe context
262K
Memory
7.3 GB / 16.0 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 | A | Runs well | 75.8 tok/s | 1392 ms | 262K |
| Coding | A | Runs well | 75.8 tok/s | 2553 ms | 262K |
| Agentic Coding | A | Runs well | 75.8 tok/s | 3713 ms | 262K |
| Reasoning | A | Runs well | 75.8 tok/s | 3017 ms | 262K |
| RAG | A | Runs well | 75.8 tok/s | 4641 ms | 262K |
How Codestral Mamba 7B (7B params) fits at each quantization level on RX 6800 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | A72 |
Q3_K_S | 3 | 3.4 GB | Low | A72 |
NVFP4 | 4 |
Copy-paste commands to run Codestral Mamba 7B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "mistralai/Mamba-Codestral-7B-v0.1" \
--hf-file "Mamba-Codestral-7B-v0.1-Q4_K_M.gguf" \
-c 4096 -ngl 99Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 9B | S | 55.1 tok/s | ||
| 14B | S | 35.6 tok/s |
Yes, RX 6800 16GB can run Codestral Mamba 7B with a A grade (Runs well). Expected decode speed: 75.8 tok/s.
Codestral Mamba 7B (7B parameters) requires approximately 7.3 GB of memory with Q4_K_M quantization.
The recommended quantization for Codestral Mamba 7B is Q4_K_M, which balances quality and memory efficiency.
On RX 6800 16GB, Codestral Mamba 7B achieves approximately 75.8 tokens per second decode speed with a time-to-first-token of 2553ms using Q4_K_M quantization.
For coding workloads, Codestral Mamba 7B on RX 6800 16GB receives a A grade with 75.8 tok/s and 262K context.
On RX 6800 16GB, Codestral Mamba 7B can safely use up to 262K tokens of context. The model's official context limit is 262K, 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-mamba-7b-on-rx-6800-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
3.9 GB |
| Medium |
| A73 |
Q4_K_M | 4 | 4.3 GB | Medium | A73 |
Q5_K_M | 5 | 5.0 GB | High | A74 |
Q6_K | 6 | 5.7 GB | High | A75 |
Q8_0Best for your GPU | 8 | 7.5 GB | Very High | A76 |
F16 | 16 | 14.3 GB | Maximum | F0 |
| 8B | S | 62 tok/s |
| 14.7B | S | 33.8 tok/s |
| 21B | A | 32.6 tok/s |