Back to search results
Qwen3-1.7B · IQ2_M
Intel Arc A770 16GB16GBvLLM v0.51L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (IQ2_M) on Intel Arc A770 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
126.29 tok/s
Decode
Decode speed
653.57 tok/s
Prefill
Prefill speed
0.3 s
TTFT
Time to first token
3.96 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 · IQ3_S Decode 111.64 · Prefill 517.56 ·
- Ollama · IQ3_S Decode 103.21 · Prefill 548.41 ·
- Ollama · Q6_K Decode 64.36 · Prefill 230.55 ·
- vLLM · IQ2_M (current)Decode 126.29 · Prefill 653.57 ·
- Ollama · Q5_K_S Decode 71.4 · Prefill 359.98 ·
Core figures
- Decode (avg)
- 126.29 tok/s
- Prefill (avg)
- 653.57 tok/s
- TTFT (avg)
- 0.3 s
- VRAM (avg)
- 3.96 GB
- MTP acceptance rate
- —
- TTFB
- 1.01 GB
- Power draw
- 192.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- IQ2_M
- Framework
- vLLM
- Version
- v0.51
- Context length
- 32768 tokens
- Batch size
- 16
- 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
- Intel Arc A770 16GB
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 3.96 GB
- OS
- Ubuntu 24.04
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 192.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · Ubuntu 24.04 · CUDA 12.6 · 32768 ctx
126.29 tok/s
Decode
653.57 tok/s
Prefill
0.3 s
TTFT
3.96 GB
VRAM
—
MTP
192.7 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=97 running model_id=55 at IQ2_M