Qwen3.5-35B-A3B · Q4_K_S
This page aggregates 1 real-world runs of Qwen3.5-35B-A3B (Q4_K_S) on Apple M4 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
115.9 tok/s
Decode
Decode speed
629 tok/s
Prefill
Prefill speed
2.35 s
TTFT
Time to first token
61.07 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · IQ4_XS Decode 115.28 · Prefill 541.34 ·
- vLLM · Q4_K_S (current)Decode 115.9 · Prefill 629 ·
- Ollama · IQ2_XS Decode 138.01 · Prefill 631.53 ·
Core figures
- Decode (avg)
- 115.9 tok/s
- Prefill (avg)
- 629 tok/s
- TTFT (avg)
- 2.35 s
- VRAM (avg)
- 61.07 GB
- MTP acceptance rate
- —
- TTFB
- 0.93 GB
- Power draw
- 65.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-35B-A3B
- Quantization
- Q4_K_S
- Framework
- vLLM
- Version
- v0.44
- Context length
- 2048 tokens
- Batch size
- 8
- GPU layers
- 999
- Flash Attention
- Off
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)
- 61.07 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Max
- CUDA
- N/A
- Power draw
- 65.6 W
Get started
Original model resources
Base model resources may not match this quantization. Use the verified deployment weights above when available.
Sources & evidence
1 measured records in total, each traceable to its original source
v0.44 · macOS 15.0 · CUDA N/A · 2048 ctx
115.9 tok/s
Decode
629 tok/s
Prefill
2.35 s
TTFT
61.07 GB
VRAM
—
MTP
65.6 W
Power draw
L2 batch seed 2026-10-10: vLLM on hw_id=26 running model_id=15 at Q4_K_S