Ternary Bonsai 2 27B · PTQ1_0
This page aggregates 1 real-world runs of Ternary Bonsai 2 27B (PTQ1_0) on NVIDIA RTX 5060 Ti 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
8.1 tok/s
Decode
Decode speed
21.87 tok/s
Prefill
Prefill speed
— s
TTFT
Time to first token
— GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
GitHub
Source platforms
Yesterday
Last verified
Performance
- llama.cpp · PTQ1_0 (current)Decode 8.1 · Prefill 21.87 ·
Core figures
- Decode (avg)
- 8.1 tok/s
- Prefill (avg)
- 21.87 tok/s
- TTFT (avg)
- — s
- VRAM (avg)
- — GB
- MTP acceptance rate
- —
- TTFB
- — GB
- Power draw
- — W
Configuration
Member-level fields are taken from the most recent run
- Model
- Ternary Bonsai 2 27B
- Quantization
- PTQ1_0
- Framework
- llama.cpp
- Version
- b11047
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5060 Ti 16GB
- Nominal VRAM
- 16 GB
- OS
- Windows 11
Get started
Original model resources
Base model resources may not match this quantization. Use the verified deployment weights above when available.
Sources & evidence
1 measured records in total, each traceable to its original source
b11047 · Windows 11
8.1 tok/s
Decode
21.87 tok/s
Prefill
— s
TTFT
0 GB
VRAM
—
MTP
— W
Power draw
pp512 @ d154855 | 21.87 ; tg32 @ d154855 | 8.10 ... That is a ~21x prefill collapse and ~5.5x decode collapse at depth