Codestral Mamba 7B needs ~7.3 GB VRAM. NVIDIA T4 16GB has 16.0 GB. With Q4_K_M quantization, expect ~56 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
56.0 tok/s
TTFT
3456 ms
Safe context
262K
Memory
7.3 GB / 16.0 GB
This setup is broadly balanced for this model.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 56.0 tok/s | 1885 ms | 262K |
| Coding | A | Runs well | 56.0 tok/s | 3456 ms | 262K |
| Agentic Coding | A | Runs well | 56.0 tok/s | 5027 ms | 262K |
| Reasoning | A | Runs well | 56.0 tok/s | 4084 ms | 262K |
| RAG | A | Runs well | 56.0 tok/s | 6284 ms | 262K |
How Codestral Mamba 7B (7B params) fits at each quantization level on NVIDIA T4 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 | 40.7 tok/s | ||
| 14B | S | 26.3 tok/s |
Yes, NVIDIA T4 16GB can run Codestral Mamba 7B with a A grade (Runs well). Expected decode speed: 56.0 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 NVIDIA T4 16GB, Codestral Mamba 7B achieves approximately 56.0 tokens per second decode speed with a time-to-first-token of 3456ms using Q4_K_M quantization.
For coding workloads, Codestral Mamba 7B on NVIDIA T4 16GB receives a A grade with 56.0 tok/s and 262K context.
On NVIDIA T4 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-t4-16gb" 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 | 45.8 tok/s |
| 14.7B | S | 24.9 tok/s |
| 21B | A | 23.2 tok/s |