Codestral Mamba 7B needs ~6.5 GB VRAM. RTX 5060 8GB has 8.0 GB. With Q4_K_M quantization, expect ~74 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
73.6 tok/s
TTFT
2630 ms
Safe context
67K
Memory
6.5 GB / 8.0 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 | 73.6 tok/s | 1435 ms | 67K |
| Coding | A | Runs well | 73.6 tok/s | 2630 ms | 67K |
| Agentic Coding | A | Tight fit | 73.6 tok/s | 3826 ms | 67K |
| Reasoning | A | Runs well | 73.6 tok/s | 3109 ms | 67K |
| RAG | A | Tight fit | 73.6 tok/s | 4783 ms | 67K |
How Codestral Mamba 7B (7B params) fits at each quantization level on RTX 5060 8GB (8.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | A78 |
Q3_K_S | 3 | 3.4 GB | Low | A79 |
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 | A | 29.5 tok/s | ||
| 8B | A | 38.1 tok/s |
Yes, RTX 5060 8GB can run Codestral Mamba 7B with a A grade (Runs well). Expected decode speed: 73.6 tok/s.
Codestral Mamba 7B (7B parameters) requires approximately 6.5 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 RTX 5060 8GB, Codestral Mamba 7B achieves approximately 73.6 tokens per second decode speed with a time-to-first-token of 2630ms using Q4_K_M quantization.
For coding workloads, Codestral Mamba 7B on RTX 5060 8GB receives a A grade with 73.6 tok/s and 67K context.
On RTX 5060 8GB, Codestral Mamba 7B can safely use up to 67K 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-rtx-5060-8gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| Medium |
| A78 |
Q4_K_M | 4 | 4.3 GB | Medium | A78 |
Q5_K_MBest for your GPU | 5 | 5.0 GB | High | A78 |
Q6_K | 6 | 5.7 GB | High | F0 |
Q8_0 | 8 | 7.5 GB | Very High | F0 |
F16 | 16 | 14.3 GB | Maximum | F0 |
| 8B | A | 40.4 tok/s |
| 8B | A | 40.4 tok/s |
| 8B | A | 38.1 tok/s |