Back to search results
Qwen3-8B · Q2_K
Apple M4 Max128GBllama.cpp v0.48L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q2_K) on Apple M4 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
238 tok/s
Decode
Decode speed
1,037.55 tok/s
Prefill
Prefill speed
1.25 s
TTFT
Time to first token
11.34 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · Q2_K (current)Decode 238 · Prefill 1037.55 ·
- llama.cpp · Q3_K_L Decode 189.78 · Prefill 777.5 ·
- vLLM · FP16 Decode 103.62 · Prefill 346.91 ·
- vLLM · IQ1_S Decode 287.05 · Prefill 1522.92 ·
- Ollama · FP16 Decode 81 · Prefill 424.01 ·
- Ollama · IQ4_XS Decode 182.06 · Prefill 996.81 ·
Core figures
- Decode (avg)
- 238 tok/s
- Prefill (avg)
- 1,037.55 tok/s
- TTFT (avg)
- 1.25 s
- VRAM (avg)
- 11.34 GB
- MTP acceptance rate
- —
- TTFB
- 1.9 GB
- Power draw
- 58.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q2_K
- Framework
- llama.cpp
- Version
- v0.48
- 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 M4 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 11.34 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Max
- CUDA
- N/A
- Power draw
- 58.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.48 · macOS 15.0 · CUDA N/A · 2048 ctx
238 tok/s
Decode
1,037.55 tok/s
Prefill
1.25 s
TTFT
11.34 GB
VRAM
—
MTP
58.8 W
Power draw
L2 batch seed 2026-10-10: llama.cpp on hw_id=26 running model_id=53 at Q2_K