Mistral 7B v0.1
mistralai/Mistral-7B-v0.1
Parameters
7.2B
Context
8K
Downloads
629.5K
Likes
4.1K
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 21.9 GB RAM 32.9 · Disk 59.9 | 38.4 GB RAM 57.7 · Disk 85.9 | 136.1 GB RAM 204.2 · Disk 124.9 |
| FP88bit | 13.4 GB RAM 32.0 · Disk 49.5 | 29.6 GB RAM 44.4 · Disk 75.5 | 126.9 GB RAM 190.3 · Disk 114.5 |
| INT88bit | 13.4 GB RAM 32.0 · Disk 49.5 | 29.6 GB RAM 44.4 · Disk 75.5 | 126.9 GB RAM 190.3 · Disk 114.5 |
| AWQ4bit | 9.4 GB RAM 32.0 · Disk 44.4 | 25.3 GB RAM 38.0 · Disk 70.4 | 122.4 GB RAM 183.6 · Disk 109.4 |
| GPTQ4bit | 9.4 GB RAM 32.0 · Disk 44.5 | 25.4 GB RAM 38.0 · Disk 70.5 | 122.5 GB RAM 183.7 · Disk 109.5 |
| GGUF4bit | 9.5 GB RAM 32.0 · Disk 44.6 | 25.5 GB RAM 38.2 · Disk 70.6 | 122.6 GB RAM 183.9 · Disk 109.6 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 514.9 tok/s
Effective production throughput ≈ 360.4 tok/s
score 0.6869
2× Tesla V100
32 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6363
8× H200 SXM
1128 GB VRAM
≈ 4413.8 tok/s
Effective production throughput ≈ 3089.7 tok/s
score 0.2197
1× RTX A6000
48 GB VRAM
≈ 220.7 tok/s
Effective production throughput ≈ 154.5 tok/s
score 0.6317
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX A6000
48 GB VRAM
$210
/mo · vast
RTX 5090
32 GB VRAM
$244
/mo · vast
L40S
48 GB VRAM
$341
/mo · vast
RTX PRO 6000 WS
48 GB VRAM
$586
/mo · vast
A100 80GB
80 GB VRAM
$876
/mo · vast