Qwen3.8-27B · IQ3_S
This page aggregates 1 real-world runs of Qwen3.8-27B (IQ3_S) on Apple M4 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
228.14 tok/s
Decode
Decode speed
1,118.4 tok/s
Prefill
Prefill speed
1.99 s
TTFT
Time to first token
39.52 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · Q5_K_S Decode 122.2 · Prefill 481.39 ·
- Strata · IQ2_M Decode 265.43 · Prefill 1342.3 ·
- Strata · IQ3_S (current)Decode 228.14 · Prefill 1118.4 ·
- llama.cpp · Q4_K_M Decode 26 · Prefill 195 ·
Core figures
- Decode (avg)
- 228.14 tok/s
- Prefill (avg)
- 1,118.4 tok/s
- TTFT (avg)
- 1.99 s
- VRAM (avg)
- 39.52 GB
- MTP acceptance rate
- 0.67
- TTFB
- 1.83 GB
- Power draw
- 53.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-27B
- Quantization
- IQ3_S
- Framework
- Strata
- Version
- v0.36
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 8
- 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)
- 39.52 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Max
- CUDA
- N/A
- Power draw
- 53.1 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
v0.36 · macOS 15.0 · CUDA N/A · 2048 ctx
228.14 tok/s
Decode
1,118.4 tok/s
Prefill
1.99 s
TTFT
39.52 GB
VRAM
0.67
MTP
53.1 W
Power draw
L2 batch seed 2026-10-10: Strata on hw_id=26 running model_id=5 at IQ3_S