Back to search results
Qwen3-1.7B · Q6_K
Apple M1 MaxStrata v0.33L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q6_K) on Apple M1 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
152.31 tok/s
Decode
Decode speed
609.9 tok/s
Prefill
Prefill speed
1.97 s
TTFT
Time to first token
5.67 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q4_K_S Decode 157.62 · Prefill 743.87 ·
- Strata · IQ4_XS Decode 217.54 · Prefill 1114.27 ·
- Strata · Q6_K (current)Decode 152.31 · Prefill 609.9 ·
Core figures
- Decode (avg)
- 152.31 tok/s
- Prefill (avg)
- 609.9 tok/s
- TTFT (avg)
- 1.97 s
- VRAM (avg)
- 5.67 GB
- MTP acceptance rate
- 0.66
- TTFB
- 1.22 GB
- Power draw
- 29 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q6_K
- Framework
- Strata
- Version
- v0.33
- Context length
- 8192 tokens
- Batch size
- 1024
- GPU layers
- 15
- Flash Attention
- Off
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)
- 5.67 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Max
- CUDA
- N/A
- Power draw
- 29 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.33 · macOS 15.0 · CUDA N/A · 8192 ctx
152.31 tok/s
Decode
609.9 tok/s
Prefill
1.97 s
TTFT
5.67 GB
VRAM
0.66
MTP
29 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=101 running model_id=55 at Q6_K