Back to search results
Qwen3.8-9B · Q4_K_S
Apple M1 Maxllama.cpp v0.28L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q4_K_S) on Apple M1 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
83.02 tok/s
Decode
Decode speed
308.94 tok/s
Prefill
Prefill speed
1.57 s
TTFT
Time to first token
16.84 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · IQ3_S Decode 82.95 · Prefill 300.79 ·
- llama.cpp · Q4_K_S (current)Decode 83.02 · Prefill 308.94 ·
- Ollama · Q2_K Decode 100.43 · Prefill 476.64 ·
- Ollama · Q5_K_S Decode 62.86 · Prefill 246.16 ·
Core figures
- Decode (avg)
- 83.02 tok/s
- Prefill (avg)
- 308.94 tok/s
- TTFT (avg)
- 1.57 s
- VRAM (avg)
- 16.84 GB
- MTP acceptance rate
- —
- TTFB
- 0.66 GB
- Power draw
- 64 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q4_K_S
- Framework
- llama.cpp
- Version
- v0.28
- Context length
- 32768 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 M1 Max
- Measured VRAM (avg)
- 16.84 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Max
- CUDA
- N/A
- Power draw
- 64 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.28 · macOS 15.0 · CUDA N/A · 32768 ctx
83.02 tok/s
Decode
308.94 tok/s
Prefill
1.57 s
TTFT
16.84 GB
VRAM
—
MTP
64 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=101 running model_id=52 at Q4_K_S