Yi-Coder 9B
01-ai/Yi-Coder-9B
Parameters
8.8B
Context
128K
Downloads
7.8K
Likes
46
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 25.7 GB RAM 38.5 · Disk 64.6 | 42.4 GB RAM 63.6 · Disk 90.6 | 140.2 GB RAM 210.3 · Disk 129.6 |
| FP88bit | 15.3 GB RAM 32.0 · Disk 51.8 | 31.5 GB RAM 47.3 · Disk 77.8 | 128.9 GB RAM 193.4 · Disk 116.8 |
| INT88bit | 15.3 GB RAM 32.0 · Disk 51.8 | 31.5 GB RAM 47.3 · Disk 77.8 | 128.9 GB RAM 193.4 · Disk 116.8 |
| AWQ4bit | 10.3 GB RAM 32.0 · Disk 45.6 | 26.3 GB RAM 39.5 · Disk 71.6 | 123.5 GB RAM 185.2 · Disk 110.6 |
| GPTQ4bit | 10.4 GB RAM 32.0 · Disk 45.7 | 26.4 GB RAM 39.6 · Disk 71.7 | 123.5 GB RAM 185.3 · Disk 110.7 |
| GGUF4bit | 10.5 GB RAM 32.0 · Disk 45.9 | 26.5 GB RAM 39.8 · Disk 71.9 | 123.7 GB RAM 185.5 · Disk 110.9 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 421.6 tok/s
Effective production throughput ≈ 295.1 tok/s
score 0.6784
2× Tesla V100
32 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6278
8× H200 SXM
1128 GB VRAM
≈ 3614.1 tok/s
Effective production throughput ≈ 2529.9 tok/s
score 0.2197
1× RTX A6000
48 GB VRAM
≈ 180.7 tok/s
Effective production throughput ≈ 126.5 tok/s
score 0.6373
💬 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