Stable Code 3B
stabilityai/stable-code-3b
Parameters
3B
Context
16K
Downloads
5.3K
Likes
666
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 14.4 GB RAM 32.0 · Disk 47.7 | 16.2 GB RAM 32.0 · Disk 73.7 | 19.3 GB RAM 32.0 · Disk 112.7 |
| FP88bit | 8.8 GB RAM 32.0 · Disk 43.4 | 10.4 GB RAM 32.0 · Disk 69.4 | 13.2 GB RAM 32.0 · Disk 108.4 |
| INT88bit | 8.8 GB RAM 32.0 · Disk 43.4 | 10.4 GB RAM 32.0 · Disk 69.4 | 13.2 GB RAM 32.0 · Disk 108.4 |
| AWQ4bit | 6.2 GB RAM 32.0 · Disk 41.3 | 7.6 GB RAM 32.0 · Disk 67.3 | 10.3 GB RAM 32.0 · Disk 106.3 |
| GPTQ4bit | 6.2 GB RAM 32.0 · Disk 41.3 | 7.6 GB RAM 32.0 · Disk 67.3 | 10.4 GB RAM 32.0 · Disk 106.3 |
| GGUF4bit | 6.3 GB RAM 32.0 · Disk 41.3 | 7.7 GB RAM 32.0 · Disk 67.3 | 10.4 GB RAM 32.0 · Disk 106.3 |
GPU Recommendations
1× RTX 3080 Ti
12 GB VRAM
≈ 20.4 img/min
Effective production throughput ≈ 14.3 images/min
score 0.6638
1× Tesla V100
16 GB VRAM
≈ 0 img/min (N/A — benchmark unavailable)
Effective production throughput ≈ 0 images/min
score 0.6159
8× RTX 5090
256 GB VRAM
≈ 501.6 img/min
Effective production throughput ≈ 351.1 images/min
score 0.3522
1× RTX 4060 Ti
8 GB VRAM
≈ 13.5 img/min
Effective production throughput ≈ 9.5 images/min
score 0.6375
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$35.7
/mo · vast
RTX 4060 Ti
8 GB VRAM
$59.2
/mo · vast
RTX 3080
10 GB VRAM
$63.8
/mo · vast
L4
24 GB VRAM
$76.2
/mo · vast
RTX 5060 Ti
8 GB VRAM
$78.3
/mo · vast