Back to search results
Qwen3-1.7B · IQ3_S
Intel Arc A770 16GB16GBllama.cpp v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (IQ3_S) on Intel Arc A770 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
111.64 tok/s
Decode
Decode speed
517.56 tok/s
Prefill
Prefill speed
0.34 s
TTFT
Time to first token
4.45 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · IQ3_S (current)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 Decode 126.29 · Prefill 653.57 ·
- Ollama · Q5_K_S Decode 71.4 · Prefill 359.98 ·
Core figures
- Decode (avg)
- 111.64 tok/s
- Prefill (avg)
- 517.56 tok/s
- TTFT (avg)
- 0.34 s
- VRAM (avg)
- 4.45 GB
- MTP acceptance rate
- —
- TTFB
- 0.89 GB
- Power draw
- 216.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- IQ3_S
- Framework
- llama.cpp
- Version
- v0.40
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 33
- 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)
- 4.45 GB
- OS
- Windows 11 23H2
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 216.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · Windows 11 23H2 · CUDA 12.6 · 8192 ctx
111.64 tok/s
Decode
517.56 tok/s
Prefill
0.34 s
TTFT
4.45 GB
VRAM
—
MTP
216.6 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=97 running model_id=55 at IQ3_S