Back to search results
Qwen3.8-9B · Q3_K_M
Intel Arc A770 16GB16GBOllama v0.27L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_M) on Intel Arc A770 16GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
48.12 tok/s
Decode
Decode speed
253.93 tok/s
Prefill
Prefill speed
1.25 s
TTFT
Time to first token
14.95 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · Q2_K Decode 60.4 · Prefill 264.17 ·
- Ollama · Q3_K_M (current)Decode 48.12 · Prefill 253.93 ·
- llama.cpp · IQ3_S Decode 55.24 · Prefill 230.96 ·
- llama.cpp · IQ4_XS Decode 48.79 · Prefill 201.84 ·
- Strata · Q3_K_L Decode 74.94 · Prefill 246.54 ·
Core figures
- Decode (avg)
- 48.12 tok/s
- Prefill (avg)
- 253.93 tok/s
- TTFT (avg)
- 1.25 s
- VRAM (avg)
- 14.95 GB
- MTP acceptance rate
- —
- TTFB
- 0.38 GB
- Power draw
- 221.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q3_K_M
- Framework
- Ollama
- Version
- v0.27
- Context length
- 2048 tokens
- Batch size
- 256
- 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)
- 14.95 GB
- OS
- Windows 11 23H2
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 221.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.27 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx
48.12 tok/s
Decode
253.93 tok/s
Prefill
1.25 s
TTFT
14.95 GB
VRAM
—
MTP
221.4 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=97 running model_id=52 at Q3_K_M