Back to search results
Qwen3-4B · IQ4_XS
Apple M5 Max128GBStrata v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (IQ4_XS) on Apple M5 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
357.04 tok/s
Decode
Decode speed
1,403.97 tok/s
Prefill
Prefill speed
0.83 s
TTFT
Time to first token
8.32 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · Q3_K_L Decode 253.55 · Prefill 980.61 ·
- Ollama · IQ2_XS Decode 308.45 · Prefill 1307.27 ·
- Ollama · IQ3_XS Decode 249.13 · Prefill 1132.99 ·
- Ollama · Q5_K_M Decode 194.79 · Prefill 989.8 ·
- Strata · IQ4_XS (current)Decode 357.04 · Prefill 1403.97 ·
Core figures
- Decode (avg)
- 357.04 tok/s
- Prefill (avg)
- 1,403.97 tok/s
- TTFT (avg)
- 0.83 s
- VRAM (avg)
- 8.32 GB
- MTP acceptance rate
- 0.77
- TTFB
- 2.86 GB
- Power draw
- 138 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- IQ4_XS
- Framework
- Strata
- Version
- v0.54
- Context length
- 16384 tokens
- Batch size
- 256
- GPU layers
- 15
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 8.32 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Max
- CUDA
- N/A
- Power draw
- 138 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · macOS 15.0 · CUDA N/A · 16384 ctx
357.04 tok/s
Decode
1,403.97 tok/s
Prefill
0.83 s
TTFT
8.32 GB
VRAM
0.77
MTP
138 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=28 running model_id=54 at IQ4_XS