Back to search results
Qwen3.5-0.8B · IQ2_M
Apple M5 Ultra512GBOllama v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ2_M) on Apple M5 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
328.08 tok/s
Decode
Decode speed
1,800.71 tok/s
Prefill
Prefill speed
0.44 s
TTFT
Time to first token
2.97 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · Q8_0 Decode 165.05 · Prefill 859.2 ·
- Ollama · IQ2_M (current)Decode 328.08 · Prefill 1800.71 ·
- Ollama · IQ3_XS Decode 260.88 · Prefill 1003.67 ·
Core figures
- Decode (avg)
- 328.08 tok/s
- Prefill (avg)
- 1,800.71 tok/s
- TTFT (avg)
- 0.44 s
- VRAM (avg)
- 2.97 GB
- MTP acceptance rate
- —
- TTFB
- 2.62 GB
- Power draw
- 123.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ2_M
- Framework
- Ollama
- Version
- v0.54
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M5 Ultra
- Nominal VRAM
- 512 GB
- Measured VRAM (avg)
- 2.97 GB
- OS
- macOS 26.1
- Power draw
- 123.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · macOS 26.1 · 2048 ctx
328.08 tok/s
Decode
1,800.71 tok/s
Prefill
0.44 s
TTFT
2.97 GB
VRAM
—
MTP
123.3 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=29 running model_id=51 at IQ2_M