Back to search results
Qwen3.5-0.8B · Q8_0
Apple M3 Max36GBStrata v0.23L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q8_0) on Apple M3 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
237.48 tok/s
Decode
Decode speed
1,069.27 tok/s
Prefill
Prefill speed
0.92 s
TTFT
Time to first token
4.03 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ2_XS Decode 369.47 · Prefill 2026.25 ·
- llama.cpp · IQ3_XS Decode 313.86 · Prefill 1064.12 ·
- Ollama · Q3_K_M Decode 286.62 · Prefill 1285.71 ·
- Strata · Q8_0 (current)Decode 237.48 · Prefill 1069.27 ·
Core figures
- Decode (avg)
- 237.48 tok/s
- Prefill (avg)
- 1,069.27 tok/s
- TTFT (avg)
- 0.92 s
- VRAM (avg)
- 4.03 GB
- MTP acceptance rate
- 0.53
- TTFB
- 1.9 GB
- Power draw
- 44.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q8_0
- Framework
- Strata
- Version
- v0.23
- Context length
- 2048 tokens
- Batch size
- 512
- 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
- Apple M3 Max
- Nominal VRAM
- 36 GB
- Measured VRAM (avg)
- 4.03 GB
- OS
- macOS 15.0
- Driver
- Apple M3 Max
- CUDA
- N/A
- Power draw
- 44.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.23 · macOS 15.0 · CUDA N/A · 2048 ctx
237.48 tok/s
Decode
1,069.27 tok/s
Prefill
0.92 s
TTFT
4.03 GB
VRAM
0.53
MTP
44.3 W
Power draw
L2 batch seed 2026-10-10: Strata on hw_id=4 running model_id=51 at Q8_0