Back to search results
Qwen3.5-0.8B · Q6_K
Apple M2 Ultrallama.cpp v0.25L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q6_K) on Apple M2 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
188.49 tok/s
Decode
Decode speed
853.9 tok/s
Prefill
Prefill speed
1.52 s
TTFT
Time to first token
3.78 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 · IQ1_S Decode 344.97 · Prefill 1343.81 ·
- llama.cpp · Q6_K (current)Decode 188.49 · Prefill 853.9 ·
- Ollama · FP16 Decode 117 · Prefill 552.38 ·
- Ollama · Q8_0 Decode 150.72 · Prefill 712.42 ·
- Ollama · IQ4_XS Decode 235.75 · Prefill 979.9 ·
- Strata · Q3_K_L Decode 328.49 · Prefill 1202.75 ·
- Strata · Q8_0 Decode 256.65 · Prefill 954.91 ·
Core figures
- Decode (avg)
- 188.49 tok/s
- Prefill (avg)
- 853.9 tok/s
- TTFT (avg)
- 1.52 s
- VRAM (avg)
- 3.78 GB
- MTP acceptance rate
- —
- TTFB
- 1.51 GB
- Power draw
- 145.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q6_K
- Framework
- llama.cpp
- Version
- v0.25
- Context length
- 16384 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M2 Ultra
- Measured VRAM (avg)
- 3.78 GB
- OS
- macOS 26.1
- Power draw
- 145.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.25 · macOS 26.1 · 16384 ctx
188.49 tok/s
Decode
853.9 tok/s
Prefill
1.52 s
TTFT
3.78 GB
VRAM
—
MTP
145.2 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=103 running model_id=51 at Q6_K