Back to search results
Qwen2.5-0.5B-Instruct · Q3_K_M
NVIDIA RTX 407012GBvLLM v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (Q3_K_M) on NVIDIA RTX 4070 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
277.32 tok/s
Decode
Decode speed
1,224.46 tok/s
Prefill
Prefill speed
0.72 s
TTFT
Time to first token
2.81 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ1_S Decode 330.62 · Prefill 1805.64 ·
- llama.cpp · Q5_K_S Decode 179.43 · Prefill 799.81 ·
- vLLM · IQ2_M Decode 318.42 · Prefill 1565.27 ·
- vLLM · Q3_K_M (current)Decode 277.32 · Prefill 1224.46 ·
Core figures
- Decode (avg)
- 277.32 tok/s
- Prefill (avg)
- 1,224.46 tok/s
- TTFT (avg)
- 0.72 s
- VRAM (avg)
- 2.81 GB
- MTP acceptance rate
- —
- TTFB
- 2.22 GB
- Power draw
- 240.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- Q3_K_M
- Framework
- vLLM
- Version
- v0.54
- Context length
- 2048 tokens
- Batch size
- 32
- 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 4070
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 2.81 GB
- OS
- Ubuntu 24.04
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 240.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx
277.32 tok/s
Decode
1,224.46 tok/s
Prefill
0.72 s
TTFT
2.81 GB
VRAM
—
MTP
240.4 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=45 running model_id=59 at Q3_K_M