DeepSeek-Coder 1.3B
deepseek-ai/deepseek-coder-1.3b-instruct
Parameters
1.3B
Context
16K
Downloads
105.8K
Likes
176
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 8.0 GB RAM 32.0 · Disk 42.8 | 23.9 GB RAM 35.9 · Disk 68.8 | 120.9 GB RAM 181.4 · Disk 107.8 |
| FP88bit | 6.5 GB RAM 32.0 · Disk 40.9 | 22.3 GB RAM 33.5 · Disk 66.9 | 119.3 GB RAM 178.9 · Disk 105.9 |
| INT88bit | 6.5 GB RAM 32.0 · Disk 40.9 | 22.3 GB RAM 33.5 · Disk 66.9 | 119.3 GB RAM 178.9 · Disk 105.9 |
| AWQ4bit | 5.7 GB RAM 32.0 · Disk 40.0 | 21.5 GB RAM 32.3 · Disk 66.0 | 118.5 GB RAM 177.7 · Disk 105.0 |
| GPTQ4bit | 5.8 GB RAM 32.0 · Disk 40.0 | 21.5 GB RAM 32.3 · Disk 66.0 | 118.5 GB RAM 177.7 · Disk 105.0 |
| GGUF4bit | 5.8 GB RAM 32.0 · Disk 40.0 | 21.6 GB RAM 32.3 · Disk 66.0 | 118.5 GB RAM 177.8 · Disk 105.0 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 2844.4 tok/s
Effective production throughput ≈ 1991.1 tok/s
score 0.6771
2× Tesla V100
32 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6265
8× H200 SXM
1128 GB VRAM
≈ 24381 tok/s
Effective production throughput ≈ 17066.7 tok/s
score 0.2197
1× RTX 3090
24 GB VRAM
≈ 1485.7 tok/s
Effective production throughput ≈ 1040 tok/s
score 0.6558
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX 3090
24 GB VRAM
$78.7
/mo · vast
RTX 4090
24 GB VRAM
$98.1
/mo · vast
RTX 4090D
24 GB VRAM
$117
/mo · vast
L4
24 GB VRAM
$148
/mo · vast
A10
24 GB VRAM
$176
/mo · vast