Back to search results
Qwen3-Coder-Next · Q3_K_S
Apple M2 ProvLLM v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Coder-Next (Q3_K_S) on Apple M2 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
89.59 tok/s
Decode
Decode speed
433.4 tok/s
Prefill
Prefill speed
1.13 s
TTFT
Time to first token
1.05 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 · Q5_K_M Decode 54.45 · Prefill 244.86 ·
- vLLM · Q3_K_S (current)Decode 89.59 · Prefill 433.4 ·
Core figures
- Decode (avg)
- 89.59 tok/s
- Prefill (avg)
- 433.4 tok/s
- TTFT (avg)
- 1.13 s
- VRAM (avg)
- 1.05 GB
- MTP acceptance rate
- —
- TTFB
- 0.72 GB
- Power draw
- 27.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Coder-Next
- Quantization
- Q3_K_S
- Framework
- vLLM
- Version
- v0.40
- Context length
- 4096 tokens
- Batch size
- 32
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M2 Pro
- Measured VRAM (avg)
- 1.05 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Pro
- CUDA
- N/A
- Power draw
- 27.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · macOS 15.0 · CUDA N/A · 4096 ctx
89.59 tok/s
Decode
433.4 tok/s
Prefill
1.13 s
TTFT
1.05 GB
VRAM
—
MTP
27.1 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=102 running model_id=58 at Q3_K_S