Back to search results
Qwen3-8B · Q5_K_S
Intel Arc A770 16GB16GBStrata v0.33L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q5_K_S) on Intel Arc A770 16GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
62.82 tok/s
Decode
Decode speed
302.98 tok/s
Prefill
Prefill speed
1.51 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
- llama.cpp · Q3_K_L Decode 56.14 · Prefill 200.64 ·
- Ollama · Q5_K_S Decode 43.29 · Prefill 237.98 ·
- Strata · Q3_K_L Decode 82.65 · Prefill 307.54 ·
- Strata · Q5_K_S (current)Decode 62.82 · Prefill 302.98 ·
Core figures
- Decode (avg)
- 62.82 tok/s
- Prefill (avg)
- 302.98 tok/s
- TTFT (avg)
- 1.51 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- 0.47
- TTFB
- 0.5 GB
- Power draw
- 222.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q5_K_S
- Framework
- Strata
- Version
- v0.33
- Context length
- 4096 tokens
- Batch size
- 1024
- GPU layers
- 8
- 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
- 222.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.33 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx
62.82 tok/s
Decode
302.98 tok/s
Prefill
1.51 s
TTFT
15.2 GB
VRAM
0.47
MTP
222.1 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=97 running model_id=53 at Q5_K_S