Qwen3-1.7B · Q6_K
This page aggregates 2 real-world runs of Qwen3-1.7B (Q6_K) on Intel Arc A770 16GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
64.36 tok/s
Decode
Decode speed
230.55 tok/s
Prefill
Prefill speed
1.72 s
TTFT
Time to first token
5.67 GB
VRAM
VRAM usage
2
Measured runs
1
Independent sources
Other
Source platforms
2 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 (current)Decode 64.36 · Prefill 230.55 ·
- vLLM · IQ2_M Decode 126.29 · Prefill 653.57 ·
- Ollama · Q5_K_S Decode 71.4 · Prefill 359.98 ·
Core figures
- Decode (avg)
- 64.36 tok/s
- Prefill (avg)
- 230.55 tok/s
- TTFT (avg)
- 1.72 s
- VRAM (avg)
- 5.67 GB
- MTP acceptance rate
- —
- TTFB
- 0.52 GB
- Power draw
- 207.15 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q6_K
- Framework
- Ollama
- Version
- v0.52
- Context length
- 8192 tokens
- Batch size
- 512
- GPU layers
- 99
- 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)
- 5.67 GB
- OS
- Windows 11 23H2
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 193.7 W
Sources & evidence
2 measured records in total, each traceable to its original source
v0.52 · Windows 11 23H2 · CUDA 12.6 · 8192 ctx
67.26 tok/s
Decode
231.26 tok/s
Prefill
1.15 s
TTFT
5.67 GB
VRAM
—
MTP
193.7 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=97 running model_id=55 at Q6_K
v0.51 · Ubuntu 24.04 · CUDA 12.6 · 32768 ctx
61.46 tok/s
Decode
229.83 tok/s
Prefill
2.3 s
TTFT
5.67 GB
VRAM
—
MTP
220.6 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=97 running model_id=55 at Q6_K