Back to search results
Qwen3-4B · Q8_0
Apple M1 MaxOllama v0.48L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (Q8_0) on Apple M1 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
64.73 tok/s
Decode
Decode speed
325.03 tok/s
Prefill
Prefill speed
2.08 s
TTFT
Time to first token
11.76 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 · Q2_K Decode 145.16 · Prefill 623.88 ·
- Ollama · IQ2_M Decode 126.39 · Prefill 412.92 ·
- Ollama · Q8_0 (current)Decode 64.73 · Prefill 325.03 ·
Core figures
- Decode (avg)
- 64.73 tok/s
- Prefill (avg)
- 325.03 tok/s
- TTFT (avg)
- 2.08 s
- VRAM (avg)
- 11.76 GB
- MTP acceptance rate
- —
- TTFB
- 0.52 GB
- Power draw
- 45.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- Q8_0
- Framework
- Ollama
- Version
- v0.48
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 28
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M1 Max
- Measured VRAM (avg)
- 11.76 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Max
- CUDA
- N/A
- Power draw
- 45.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.48 · macOS 15.0 · CUDA N/A · 4096 ctx
64.73 tok/s
Decode
325.03 tok/s
Prefill
2.08 s
TTFT
11.76 GB
VRAM
—
MTP
45.9 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=101 running model_id=54 at Q8_0