Back to search results
Qwen3-4B · Q6_K
Intel Arc A770 16GB16GBStrata v0.49L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (Q6_K) on Intel Arc A770 16GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
68.88 tok/s
Decode
Decode speed
245.03 tok/s
Prefill
Prefill speed
2.5 s
TTFT
Time to first token
10.5 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ4_XS Decode 72.03 · Prefill 234.09 ·
- Strata · Q6_K (current)Decode 68.88 · Prefill 245.03 ·
- llama.cpp · IQ1_S Decode 92.68 · Prefill 463.17 ·
- vLLM · Q5_K_S Decode 59.1 · Prefill 316.05 ·
Core figures
- Decode (avg)
- 68.88 tok/s
- Prefill (avg)
- 245.03 tok/s
- TTFT (avg)
- 2.5 s
- VRAM (avg)
- 10.5 GB
- MTP acceptance rate
- 0.65
- TTFB
- 0.55 GB
- Power draw
- 165.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- Q6_K
- Framework
- Strata
- Version
- v0.49
- Context length
- 8192 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)
- 10.5 GB
- OS
- Ubuntu 24.04
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 165.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.49 · Ubuntu 24.04 · CUDA 12.6 · 8192 ctx
68.88 tok/s
Decode
245.03 tok/s
Prefill
2.5 s
TTFT
10.5 GB
VRAM
0.65
MTP
165.5 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=97 running model_id=54 at Q6_K