Mistral Small 3.1 24B
mistralai/Mistral-Small-3.1-24B-Instruct-2503
Parameters
24B
Context
128K
Downloads
275.3K
Likes
1.4K
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 61.5 GB RAM 92.3 · Disk 108.7 | 79.8 GB RAM 119.7 · Disk 134.7 | 179.3 GB RAM 268.9 · Disk 173.7 |
| FP88bit | 33.2 GB RAM 49.8 · Disk 73.9 | 50.3 GB RAM 75.4 · Disk 99.9 | 148.5 GB RAM 222.7 · Disk 138.9 |
| INT88bit | 33.2 GB RAM 49.8 · Disk 73.9 | 50.3 GB RAM 75.4 · Disk 99.9 | 148.5 GB RAM 222.7 · Disk 138.9 |
| AWQ4bit | 19.6 GB RAM 32.0 · Disk 57.1 | 36.0 GB RAM 54.1 · Disk 83.1 | 133.6 GB RAM 200.4 · Disk 122.1 |
| GPTQ4bit | 19.8 GB RAM 32.0 · Disk 57.3 | 36.2 GB RAM 54.3 · Disk 83.3 | 133.8 GB RAM 200.7 · Disk 122.3 |
| GGUF4bit | 20.2 GB RAM 32.0 · Disk 57.7 | 36.6 GB RAM 54.9 · Disk 83.7 | 134.2 GB RAM 201.3 · Disk 122.7 |
GPU Recommendations
1× H100 SXM
80 GB VRAM
≈ 289 tok/s
Effective production throughput ≈ 202.3 tok/s
score 0.6096
4× Tesla V100
64 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5484
8× H200 SXM
1128 GB VRAM
≈ 1325.3 tok/s
Effective production throughput ≈ 927.7 tok/s
score 0.2197
1× RTX A6000
48 GB VRAM
≈ 66.3 tok/s
Effective production throughput ≈ 46.4 tok/s
score 0.6909
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX A6000
48 GB VRAM
$210
/mo · vast
L40S
48 GB VRAM
$341
/mo · vast
RTX PRO 6000 WS
48 GB VRAM
$482
/mo · vast
RTX PRO 6000 S
48 GB VRAM
$633
/mo · vast
A100 80GB
80 GB VRAM
$876
/mo · vast