Back to search results
Qwen3-8B · Q4_K_S
Apple M5 Max128GBOllama v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q4_K_S) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
185.61 tok/s
Decode
Decode speed
631.22 tok/s
Prefill
Prefill speed
0.14 s
TTFT
Time to first token
15.2 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 · IQ3_XS Decode 233.71 · Prefill 783.62 ·
- Ollama · IQ3_XS Decode 212.17 · Prefill 767.04 ·
- Ollama · Q4_K_S (current)Decode 185.61 · Prefill 631.22 ·
- llama.cpp · Q6_K Decode 137.3 · Prefill 696.86 ·
- Strata · Q4_K_M Decode 252.52 · Prefill 1255.16 ·
Core figures
- Decode (avg)
- 185.61 tok/s
- Prefill (avg)
- 631.22 tok/s
- TTFT (avg)
- 0.14 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 1.48 GB
- Power draw
- 271.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q4_K_S
- Framework
- Ollama
- Version
- v0.54
- 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 M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 15.2 GB
- OS
- Ubuntu 24.04
- Driver
- 565.57
- CUDA
- 12.4
- Power draw
- 271.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · Ubuntu 24.04 · CUDA 12.4 · 4096 ctx
185.61 tok/s
Decode
631.22 tok/s
Prefill
0.14 s
TTFT
15.2 GB
VRAM
—
MTP
271.6 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=28 running model_id=53 at Q4_K_S