Back to search results
Qwen3-1.7B · Q3_K_L
Apple M5 Max128GBOllama v0.24L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_L) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
353.08 tok/s
Decode
Decode speed
1,662.13 tok/s
Prefill
Prefill speed
1.08 s
TTFT
Time to first token
4.67 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · Q2_K Decode 302.27 · Prefill 1354.5 ·
- vLLM · Q8_0 Decode 255.36 · Prefill 1217.53 ·
- Strata · Q8_0 Decode 319.85 · Prefill 1662.65 ·
- Ollama · Q3_K_L (current)Decode 353.08 · Prefill 1662.13 ·
Core figures
- Decode (avg)
- 353.08 tok/s
- Prefill (avg)
- 1,662.13 tok/s
- TTFT (avg)
- 1.08 s
- VRAM (avg)
- 4.67 GB
- MTP acceptance rate
- —
- TTFB
- 2.82 GB
- Power draw
- 44 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q3_K_L
- Framework
- Ollama
- Version
- v0.24
- 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)
- 4.67 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Max
- CUDA
- N/A
- Power draw
- 44 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.24 · macOS 15.0 · CUDA N/A · 8192 ctx
353.08 tok/s
Decode
1,662.13 tok/s
Prefill
1.08 s
TTFT
4.67 GB
VRAM
—
MTP
44 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=28 running model_id=55 at Q3_K_L