Back to search results
Qwen3-1.7B · Q5_K_M
Apple M1llama.cpp v0.53L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q5_K_M) on Apple M1 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
75.84 tok/s
Decode
Decode speed
355.79 tok/s
Prefill
Prefill speed
0.7 s
TTFT
Time to first token
5.42 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_S Decode 97.72 · Prefill 393.93 ·
- llama.cpp · Q5_K_M (current)Decode 75.84 · Prefill 355.79 ·
- vLLM · Q4_K_M Decode 84.3 · Prefill 383.2 ·
- vLLM · Q6_K Decode 72.53 · Prefill 321.64 ·
Core figures
- Decode (avg)
- 75.84 tok/s
- Prefill (avg)
- 355.79 tok/s
- TTFT (avg)
- 0.7 s
- VRAM (avg)
- 5.42 GB
- MTP acceptance rate
- —
- TTFB
- 0.61 GB
- Power draw
- 74.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q5_K_M
- Framework
- llama.cpp
- Version
- v0.53
- Context length
- 16384 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 M1
- Measured VRAM (avg)
- 5.42 GB
- OS
- macOS 15.0
- Driver
- Apple M1
- CUDA
- N/A
- Power draw
- 74.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.53 · macOS 15.0 · CUDA N/A · 16384 ctx
75.84 tok/s
Decode
355.79 tok/s
Prefill
0.7 s
TTFT
5.42 GB
VRAM
—
MTP
74.6 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=99 running model_id=55 at Q5_K_M