Back to search results
Qwen3.5-0.8B · Q4_K_M
Apple M5 Max128GBStrata v0.31L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q4_K_M) on Apple M5 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
357.61 tok/s
Decode
Decode speed
1,232.58 tok/s
Prefill
Prefill speed
1.42 s
TTFT
Time to first token
3.48 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · Q4_K_S Decode 308.8 · Prefill 1388.47 ·
- Ollama · Q5_K_M Decode 365.7 · Prefill 1467.25 ·
- Strata · FP16 Decode 330.86 · Prefill 1157.2 ·
- Strata · Q4_K_M (current)Decode 357.61 · Prefill 1232.58 ·
- Ollama · IQ3_S Decode 329.08 · Prefill 1581.37 ·
- Ollama · Q2_K Decode 281.81 · Prefill 1519.14 ·
- Strata · IQ2_M Decode 308.09 · Prefill 1499.86 ·
Core figures
- Decode (avg)
- 357.61 tok/s
- Prefill (avg)
- 1,232.58 tok/s
- TTFT (avg)
- 1.42 s
- VRAM (avg)
- 3.48 GB
- MTP acceptance rate
- 0.49
- TTFB
- 2.86 GB
- Power draw
- 172.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q4_K_M
- Framework
- Strata
- Version
- v0.31
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 5
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 3.48 GB
- OS
- Ubuntu 22.04
- Driver
- 565.57
- CUDA
- 12.4
- Power draw
- 172.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.31 · Ubuntu 22.04 · CUDA 12.4 · 32768 ctx
357.61 tok/s
Decode
1,232.58 tok/s
Prefill
1.42 s
TTFT
3.48 GB
VRAM
0.49
MTP
172.7 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=28 running model_id=51 at Q4_K_M