Back to search results
Qwen3-8B · IQ3_XS
Apple M5 Max128GBOllama v0.33L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (IQ3_XS) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
212.17 tok/s
Decode
Decode speed
767.04 tok/s
Prefill
Prefill speed
1.28 s
TTFT
Time to first token
12.52 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 (current)Decode 212.17 · Prefill 767.04 ·
- Ollama · Q4_K_S 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)
- 212.17 tok/s
- Prefill (avg)
- 767.04 tok/s
- TTFT (avg)
- 1.28 s
- VRAM (avg)
- 12.52 GB
- MTP acceptance rate
- —
- TTFB
- 1.7 GB
- Power draw
- 276.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- IQ3_XS
- Framework
- Ollama
- Version
- v0.33
- Context length
- 8192 tokens
- Batch size
- 256
- 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)
- 12.52 GB
- OS
- Ubuntu 22.04
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 276.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.33 · Ubuntu 22.04 · CUDA 12.8 · 8192 ctx
212.17 tok/s
Decode
767.04 tok/s
Prefill
1.28 s
TTFT
12.52 GB
VRAM
—
MTP
276.7 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=28 running model_id=53 at IQ3_XS