Back to search results
Qwen3-1.7B · Q3_K_M
NVIDIA RTX 408016GBvLLM v0.34L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_M) on NVIDIA RTX 4080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
197.14 tok/s
Decode
Decode speed
742.62 tok/s
Prefill
Prefill speed
1.65 s
TTFT
Time to first token
4.53 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · IQ2_M Decode 224.82 · Prefill 990.41 ·
- vLLM · Q3_K_M (current)Decode 197.14 · Prefill 742.62 ·
- Ollama · Q4_K_S Decode 163.88 · Prefill 605 ·
- Ollama · Q8_0 Decode 101.94 · Prefill 440.86 ·
Core figures
- Decode (avg)
- 197.14 tok/s
- Prefill (avg)
- 742.62 tok/s
- TTFT (avg)
- 1.65 s
- VRAM (avg)
- 4.53 GB
- MTP acceptance rate
- —
- TTFB
- 1.58 GB
- Power draw
- 315.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q3_K_M
- Framework
- vLLM
- Version
- v0.34
- Context length
- 32768 tokens
- Batch size
- 8
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 4.53 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 12.6
- Power draw
- 315.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.34 · Ubuntu 24.04 · CUDA 12.6 · 32768 ctx
197.14 tok/s
Decode
742.62 tok/s
Prefill
1.65 s
TTFT
4.53 GB
VRAM
—
MTP
315.9 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=41 running model_id=55 at Q3_K_M