Qwen/Qwen2.5-1.5B-Instruct
Qwen/Qwen2.5-1.5B-Instruct
Parameters
1B
Context
32K
Downloads
11.6M
Likes
796
Architecture
qwen2
28 layers · 2 KV heads · head 128 · hidden 1536
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 8.5 GB RAM 32.0 · Disk 43.4 | 24.4 GB RAM 36.6 · Disk 69.4 | 121.5 GB RAM 182.2 · Disk 108.4 |
| FP88bit | 6.7 GB RAM 32.0 · Disk 41.2 | 22.6 GB RAM 33.8 · Disk 67.2 | 119.5 GB RAM 179.3 · Disk 106.2 |
| INT88bit | 6.7 GB RAM 32.0 · Disk 41.2 | 22.6 GB RAM 33.8 · Disk 67.2 | 119.5 GB RAM 179.3 · Disk 106.2 |
| AWQ4bit | 5.9 GB RAM 32.0 · Disk 40.1 | 21.7 GB RAM 32.5 · Disk 66.1 | 118.6 GB RAM 177.9 · Disk 105.1 |
| GPTQ4bit | 5.9 GB RAM 32.0 · Disk 40.1 | 21.7 GB RAM 32.5 · Disk 66.1 | 118.6 GB RAM 177.9 · Disk 105.1 |
| GGUF4bit | 5.9 GB RAM 32.0 · Disk 40.2 | 21.7 GB RAM 32.5 · Disk 66.2 | 118.6 GB RAM 178.0 · Disk 105.2 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 2488.9 tok/s
Effective production throughput ≈ 1742.2 tok/s
score 0.6779
1× RTX 3090
24 GB VRAM
≈ 1300 tok/s
Effective production throughput ≈ 910 tok/s
score 0.6544
8× H200 SXM
1128 GB VRAM
≈ 21333.3 tok/s
Effective production throughput ≈ 14933.3 tok/s
score 0.2197
1× RTX 4090
24 GB VRAM
≈ 1400 tok/s
Effective production throughput ≈ 980 tok/s
score 0.6545
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX 3090
24 GB VRAM
$76.5
/mo · vast
RTX 4090
24 GB VRAM
$99.0
/mo · vast
RTX 4090D
24 GB VRAM
$117
/mo · vast
L4
24 GB VRAM
$147
/mo · vast
A10
24 GB VRAM
$176
/mo · vast