Back to search results
Qwen3-1.7B · Q8_0
Apple M5 Max128GBvLLM v0.51L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q8_0) on Apple M5 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
255.36 tok/s
Decode
Decode speed
1,217.53 tok/s
Prefill
Prefill speed
0.73 s
TTFT
Time to first token
6.21 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q2_K Decode 302.27 · Prefill 1354.5 ·
- vLLM · Q8_0 (current)Decode 255.36 · Prefill 1217.53 ·
- Strata · Q8_0 Decode 319.85 · Prefill 1662.65 ·
- Ollama · Q3_K_L Decode 353.08 · Prefill 1662.13 ·
Core figures
- Decode (avg)
- 255.36 tok/s
- Prefill (avg)
- 1,217.53 tok/s
- TTFT (avg)
- 0.73 s
- VRAM (avg)
- 6.21 GB
- MTP acceptance rate
- —
- TTFB
- 2.04 GB
- Power draw
- 194.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q8_0
- Framework
- vLLM
- Version
- v0.51
- Context length
- 4096 tokens
- Batch size
- 32
- GPU layers
- 999
- 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)
- 6.21 GB
- OS
- Ubuntu 22.04
- Driver
- 555.85
- CUDA
- 12.6
- Power draw
- 194.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · Ubuntu 22.04 · CUDA 12.6 · 4096 ctx
255.36 tok/s
Decode
1,217.53 tok/s
Prefill
0.73 s
TTFT
6.21 GB
VRAM
—
MTP
194.9 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=28 running model_id=55 at Q8_0