mistralai/Mistral-7B-Instruct-v0.3
mistralai/Mistral-7B-Instruct-v0.3
Classic 7B Mistral, lightweight and fast.
Parameters
6.6B
Context
32K
Downloads
4.1M
Likes
2.8K
Architecture
mistral
32 layers · 8 KV heads · head 128 · hidden 4096
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 22.2 GB RAM 33.2 · Disk 60.2 | 38.7 GB RAM 58.0 · Disk 86.2 | 136.4 GB RAM 204.6 · Disk 125.2 |
| FP88bit | 13.6 GB RAM 32.0 · Disk 49.6 | 29.7 GB RAM 44.5 · Disk 75.6 | 127.0 GB RAM 190.5 · Disk 114.6 |
| INT88bit | 13.6 GB RAM 32.0 · Disk 49.6 | 29.7 GB RAM 44.5 · Disk 75.6 | 127.0 GB RAM 190.5 · Disk 114.6 |
| AWQ4bit | 9.4 GB RAM 32.0 · Disk 44.5 | 25.4 GB RAM 38.1 · Disk 70.5 | 122.5 GB RAM 183.7 · Disk 109.5 |
| GPTQ4bit | 9.5 GB RAM 32.0 · Disk 44.6 | 25.4 GB RAM 38.1 · Disk 70.6 | 122.5 GB RAM 183.8 · Disk 109.6 |
| GGUF4bit | 9.6 GB RAM 32.0 · Disk 44.7 | 25.5 GB RAM 38.3 · Disk 70.7 | 122.6 GB RAM 184.0 · Disk 109.7 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 507.6 tok/s
Effective production throughput ≈ 355.3 tok/s
score 0.6864
2× Tesla V100
32 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6358
8× H200 SXM
1128 GB VRAM
≈ 4351.3 tok/s
Effective production throughput ≈ 3045.9 tok/s
score 0.2197
1× RTX A6000
48 GB VRAM
≈ 217.6 tok/s
Effective production throughput ≈ 152.3 tok/s
score 0.632
💬 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