Back to search results
Qwen3.8-9B · IQ4_XS
Intel Arc A770 16GB16GBllama.cpp v0.32L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ4_XS) on Intel Arc A770 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
48.79 tok/s
Decode
Decode speed
201.84 tok/s
Prefill
Prefill speed
0.8 s
TTFT
Time to first token
15.2 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Ollama · Q2_K Decode 60.4 · Prefill 264.17 ·
- Ollama · Q3_K_M Decode 48.12 · Prefill 253.93 ·
- llama.cpp · IQ3_S Decode 55.24 · Prefill 230.96 ·
- llama.cpp · IQ4_XS (current)Decode 48.79 · Prefill 201.84 ·
- Strata · Q3_K_L Decode 74.94 · Prefill 246.54 ·
Core figures
- Decode (avg)
- 48.79 tok/s
- Prefill (avg)
- 201.84 tok/s
- TTFT (avg)
- 0.8 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.39 GB
- Power draw
- 248.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ4_XS
- Framework
- llama.cpp
- Version
- v0.32
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 28
- 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)
- 15.2 GB
- OS
- Ubuntu 24.04
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 248.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.32 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx
48.79 tok/s
Decode
201.84 tok/s
Prefill
0.8 s
TTFT
15.2 GB
VRAM
—
MTP
248.9 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=97 running model_id=52 at IQ4_XS