Codestral RAG 19B Pruned i1 needs ~27.5 GB VRAM. AMD Instinct MI250 128GB has 128.0 GB. With Q4_K_M quantization, expect ~188 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
187.7 tok/s
TTFT
1031 ms
Safe context
738K
Memory
27.5 GB / 128.0 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 | C | Runs well | 187.7 tok/s | 562 ms | 738K |
| Coding | C | Runs well | 187.7 tok/s | 1031 ms | 738K |
| Agentic Coding | C | Runs well | 187.7 tok/s | 1500 ms | 738K |
| Reasoning | C | Runs well | 187.7 tok/s | 1219 ms | 738K |
| RAG | C | Runs well | 187.7 tok/s | 1875 ms | 738K |
How Codestral RAG 19B Pruned i1 (19B params) fits at each quantization level on AMD Instinct MI250 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.4 GB | Low | D38 |
Q3_K_S | 3 | 9.3 GB | Low | D38 |
NVFP4 | 4 |
Copy-paste commands to run Codestral RAG 19B Pruned i1 on your machine.
Run
lms load hf-mradermacher--codestral-rag-19b-pruned-i1-gguf && lms server startYes, AMD Instinct MI250 128GB can run Codestral RAG 19B Pruned i1 with a C grade (Runs well). Expected decode speed: 187.7 tok/s.
Codestral RAG 19B Pruned i1 (19B parameters) requires approximately 27.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Codestral RAG 19B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI250 128GB, Codestral RAG 19B Pruned i1 achieves approximately 187.7 tokens per second decode speed with a time-to-first-token of 1031ms using Q4_K_M quantization.
For coding workloads, Codestral RAG 19B Pruned i1 on AMD Instinct MI250 128GB receives a C grade with 187.7 tok/s and 738K context.
On AMD Instinct MI250 128GB, Codestral RAG 19B Pruned i1 can safely use up to 738K tokens of context. The model's official context limit is —, 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/hf-mradermacher--codestral-rag-19b-pruned-i1-gguf-on-instinct-mi250-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
10.6 GB |
| Medium |
| D38 |
Q4_K_M | 4 | 11.6 GB | Medium | D38 |
Q5_K_M | 5 | 13.7 GB | High | D38 |
Q6_K | 6 | 15.6 GB | High | D38 |
Q8_0 | 8 | 20.3 GB | Very High | D39 |
F16Best for your GPU | 16 | 38.9 GB | Maximum | C41 |