Back to search results
Qwen3.8-9B · Q3_K_L
Apple M2 Ultrallama.cpp v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_L) on Apple M2 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
110.22 tok/s
Decode
Decode speed
411.86 tok/s
Prefill
Prefill speed
1.09 s
TTFT
Time to first token
15.71 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 · Q3_K_L (current)Decode 110.22 · Prefill 411.86 ·
- Ollama · IQ3_XS Decode 108.03 · Prefill 420.83 ·
- vLLM · IQ1_S Decode 152.06 · Prefill 546.19 ·
- Strata · Q4_K_M Decode 129.12 · Prefill 454.27 ·
- Strata · Q8_0 Decode 89.33 · Prefill 303.19 ·
Core figures
- Decode (avg)
- 110.22 tok/s
- Prefill (avg)
- 411.86 tok/s
- TTFT (avg)
- 1.09 s
- VRAM (avg)
- 15.71 GB
- MTP acceptance rate
- —
- TTFB
- 0.88 GB
- Power draw
- 115.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q3_K_L
- Framework
- llama.cpp
- Version
- v0.43
- Context length
- 16384 tokens
- Batch size
- 256
- GPU layers
- 99
- 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)
- 15.71 GB
- OS
- macOS 26.1
- Power draw
- 115.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · macOS 26.1 · 16384 ctx
110.22 tok/s
Decode
411.86 tok/s
Prefill
1.09 s
TTFT
15.71 GB
VRAM
—
MTP
115.8 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=103 running model_id=52 at Q3_K_L