Back to search results
Qwen3-4B · IQ3_XS
Apple M5 Max128GBOllama v0.23L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (IQ3_XS) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
249.13 tok/s
Decode
Decode speed
1,132.99 tok/s
Prefill
Prefill speed
2.37 s
TTFT
Time to first token
7.31 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 · Q3_K_L Decode 253.55 · Prefill 980.61 ·
- Ollama · IQ2_XS Decode 308.45 · Prefill 1307.27 ·
- Ollama · IQ3_XS (current)Decode 249.13 · Prefill 1132.99 ·
- Ollama · Q5_K_M Decode 194.79 · Prefill 989.8 ·
- Strata · IQ4_XS Decode 357.04 · Prefill 1403.97 ·
Core figures
- Decode (avg)
- 249.13 tok/s
- Prefill (avg)
- 1,132.99 tok/s
- TTFT (avg)
- 2.37 s
- VRAM (avg)
- 7.31 GB
- MTP acceptance rate
- —
- TTFB
- 1.99 GB
- Power draw
- 220.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- IQ3_XS
- Framework
- Ollama
- Version
- v0.23
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- Off
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)
- 7.31 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.4
- Power draw
- 220.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.23 · Windows 11 23H2 · CUDA 12.4 · 32768 ctx
249.13 tok/s
Decode
1,132.99 tok/s
Prefill
2.37 s
TTFT
7.31 GB
VRAM
—
MTP
220.7 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=28 running model_id=54 at IQ3_XS