Back to search results
Qwen3.5-0.8B · IQ3_XS
Intel Arc A770 16GB16GBStrata v0.48L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ3_XS) on Intel Arc A770 16GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
236.84 tok/s
Decode
Decode speed
822.88 tok/s
Prefill
Prefill speed
1.47 s
TTFT
Time to first token
3.14 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ2_XS Decode 182.37 · Prefill 880.77 ·
- vLLM · Q8_0 Decode 87.79 · Prefill 281.11 ·
- Strata · IQ2_M Decode 232.67 · Prefill 822.78 ·
- Strata · IQ3_XS (current)Decode 236.84 · Prefill 822.88 ·
- vLLM · Q3_K_L Decode 146.32 · Prefill 525.63 ·
- vLLM · Q5_K_M Decode 109.82 · Prefill 577.25 ·
- Ollama · Q2_K Decode 163.98 · Prefill 697.28 ·
Core figures
- Decode (avg)
- 236.84 tok/s
- Prefill (avg)
- 822.88 tok/s
- TTFT (avg)
- 1.47 s
- VRAM (avg)
- 3.14 GB
- MTP acceptance rate
- 0.67
- TTFB
- 1.89 GB
- Power draw
- 185.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ3_XS
- Framework
- Strata
- Version
- v0.48
- Context length
- 4096 tokens
- Batch size
- 1024
- GPU layers
- 8
- Flash Attention
- Off
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)
- 3.14 GB
- OS
- Windows 11 23H2
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 185.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.48 · Windows 11 23H2 · CUDA 12.6 · 4096 ctx
236.84 tok/s
Decode
822.88 tok/s
Prefill
1.47 s
TTFT
3.14 GB
VRAM
0.67
MTP
185.6 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=97 running model_id=51 at IQ3_XS