Back to search results
Qwen3-Coder-Next · IQ4_XS
Apple M1vLLM v0.51L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Coder-Next (IQ4_XS) on Apple M1 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
47.87 tok/s
Decode
Decode speed
181.96 tok/s
Prefill
Prefill speed
1.27 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
- vLLM · IQ4_XS (current)Decode 47.87 · Prefill 181.96 ·
- Ollama · FP16 Decode 21.35 · Prefill 72.87 ·
- Ollama · Q3_K_L Decode 41.49 · Prefill 134.08 ·
Core figures
- Decode (avg)
- 47.87 tok/s
- Prefill (avg)
- 181.96 tok/s
- TTFT (avg)
- 1.27 s
- VRAM (avg)
- 1.05 GB
- MTP acceptance rate
- —
- TTFB
- 0.38 GB
- Power draw
- 20.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Coder-Next
- Quantization
- IQ4_XS
- Framework
- vLLM
- Version
- v0.51
- Context length
- 32768 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 M1
- Measured VRAM (avg)
- 1.05 GB
- OS
- macOS 15.0
- Driver
- Apple M1
- CUDA
- N/A
- Power draw
- 20.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · macOS 15.0 · CUDA N/A · 32768 ctx
47.87 tok/s
Decode
181.96 tok/s
Prefill
1.27 s
TTFT
1.05 GB
VRAM
—
MTP
20.8 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=99 running model_id=58 at IQ4_XS