Qwen/Qwen3-ASR-1.7B
Qwen/Qwen3-ASR-1.7B
Parameters
2.3B
Context
—
Downloads
4.2M
Likes
1.1K
Architecture
qwen3_asr
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 13.3 GB RAM 32.0 · Disk 45.8 | 14.5 GB RAM 32.0 · Disk 71.8 | 16.4 GB RAM 32.0 · Disk 110.8 |
| FP88bit | 8.0 GB RAM 32.0 · Disk 42.4 | 9.0 GB RAM 32.0 · Disk 68.4 | 10.6 GB RAM 32.0 · Disk 107.4 |
| INT88bit | 8.0 GB RAM 32.0 · Disk 42.4 | 9.0 GB RAM 32.0 · Disk 68.4 | 10.6 GB RAM 32.0 · Disk 107.4 |
| AWQ4bit | 5.5 GB RAM 32.0 · Disk 40.8 | 6.3 GB RAM 32.0 · Disk 66.8 | 7.8 GB RAM 32.0 · Disk 105.8 |
| GPTQ4bit | 5.5 GB RAM 32.0 · Disk 40.8 | 6.4 GB RAM 32.0 · Disk 66.8 | 7.8 GB RAM 32.0 · Disk 105.8 |
| GGUF4bit | 5.6 GB RAM 32.0 · Disk 40.8 | 6.4 GB RAM 32.0 · Disk 66.8 | 7.9 GB RAM 32.0 · Disk 105.8 |
GPU Recommendations
1× RTX 3080 Ti
12 GB VRAM
≈ RTF 0.39
Effective production throughput ≈ 0.3 RTF
score 0.6355
1× Tesla V100
16 GB VRAM
≈ RTF 0 (N/A — benchmark unavailable)
Effective production throughput ≈ 0 RTF
score 0.5945
8× RTX 5090
256 GB VRAM
≈ RTF 0.06
Effective production throughput ≈ 0 RTF
score 0.3506
1× RTX 4060 Ti
8 GB VRAM
≈ RTF 1.22
Effective production throughput ≈ 0.9 RTF
score 0.6802
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$39.7
/mo · vast
RTX 4060 Ti
8 GB VRAM
$59.2
/mo · vast
RTX 3080
10 GB VRAM
$64.3
/mo · vast
RTX 5060 Ti
8 GB VRAM
$68.8
/mo · vast
RTX 4070S Ti
16 GB VRAM
$68.9
/mo · vast