Qwen/Qwen3-1.7B
Qwen/Qwen3-1.7B
Parameters
1.7B
Context
40K
Downloads
7.3M
Likes
517
Architecture
qwen3
28 layers · 8 KV heads · head 128 · hidden 2048
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 7.7 GB RAM 32.0 · Disk 44.0 | 18.6 GB RAM 32.0 · Disk 70.0 | 90.8 GB RAM 136.2 · Disk 109.0 |
| FP88bit | 5.7 GB RAM 32.0 · Disk 41.5 | 16.5 GB RAM 32.0 · Disk 67.5 | 88.6 GB RAM 132.9 · Disk 106.5 |
| INT88bit | 5.7 GB RAM 32.0 · Disk 41.5 | 16.5 GB RAM 32.0 · Disk 67.5 | 88.6 GB RAM 132.9 · Disk 106.5 |
| AWQ4bit | 4.7 GB RAM 32.0 · Disk 40.3 | 15.5 GB RAM 32.0 · Disk 66.3 | 87.6 GB RAM 131.3 · Disk 105.3 |
| GPTQ4bit | 4.7 GB RAM 32.0 · Disk 40.3 | 15.5 GB RAM 32.0 · Disk 66.3 | 87.6 GB RAM 131.3 · Disk 105.3 |
| GGUF4bit | 4.7 GB RAM 32.0 · Disk 40.3 | 15.5 GB RAM 32.0 · Disk 66.3 | 87.6 GB RAM 131.4 · Disk 105.3 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 2159 tok/s
Effective production throughput ≈ 1511.3 tok/s
score 0.6266
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6362
8× H200 SXM
1128 GB VRAM
≈ 18506 tok/s
Effective production throughput ≈ 12954.2 tok/s
score 0.2197
1× RTX 3090
24 GB VRAM
≈ 1127.7 tok/s
Effective production throughput ≈ 789.4 tok/s
score 0.6676
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$21.1
/mo · vast
RTX 3090
24 GB VRAM
$45.4
/mo · vast
RTX 4070S Ti
16 GB VRAM
$49.5
/mo · vast
RTX 5070 Ti
16 GB VRAM
$83.4
/mo · vast
RTX 4080S
16 GB VRAM
$88.3
/mo · vast