davetha/Ternary-Bonsai-2-27B-Abliterated-PQ2_0-GGUF
text-generation model by davetha
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
A format repack, not a new ablation. Same weights as BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-PTQ10-GGUF, in PQ20 instead of PTQ10, because PTQ10 has GPU kernels for NVIDIA Ampere only. On an AMD MI210 (gfx90a / CDNA2) that is a 2.2x difference: Single-stream, -ngl 99 -c 8192, one MI210, PrismML llama.cpp fork. MMQ tile configs in the PrismML fork exist per architecture. PTQ10 has entries for Ampere and nowhere else: PTQ10 is additionally #if !defined(GGMLUSEHIP)-gated in 17 places, and its eligibility test is turingmmaavailable(cc), hard-wired to NVIDIA. So on CDNA it falls back to fp16 dequantise + BLAS. PQ20 has CDNA kernels and takes the fast path. The ablated weights ship only as PTQ10, so the edit was transplanted rather than re-derived: tensors differ — ffndown, ssmout, attnoutput, blocks 15-63 — matching the source release's stated scope. Do not try to reproduce this by projecting a refusal direction out. The source card explains why, and…
Read the full model card ↗ · Preview checked 2026-10-29T10:48:47.536Z
Inside the original model card — Document outline
- Ternary-Bonsai-2-27B Abliterated — PQ20
- Why PTQ10 is slow outside Ampere
- How it was made
- Verification
- Requirements
- Attribution
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
davetha/Ternary-Bonsai-2-27B-Abliterated-PQ2_0-GGUF is a text-generation model repository published by davetha on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-18T06:21:06.000Z
- Last modified
- 2026-09-18T06:22:00.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: prism-ml/Ternary-Bonsai-2-27B-gguf, BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-PTQ1_0-GGUF
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-18T06:35:09.247Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.