prism-ml/Ternary-Bonsai-2-9B-gguf
image-text-to-text model by prism-ml
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.
Prism ML Website | Demo & Examples | Discord A 9B-class vision-language model with ternary transformer weights, for llama.cpp (CUDA, Metal, CPU). Bits/weight is file size over the 8.95B language-model parameters, so it includes the F32 tensors and metadata. The three language-model packs hold the same ternary weights; they differ only in storage layout and kernel speed. The MTP file is the PQ20 model plus one extra draft layer, so you load it instead of the plain PQ20, not alongside it. The ternary kernels live in the PrismML-Eng/llama.cpp fork (branch prism). It runs every file here, including MTP and DFlash2. Upstream llama.cpp runs only Q20 (recent master, which includes the Hadamard activation runtime); it rejects PQ20 and PTQ10 as unknown types. Vision projector: use the Q80 mmproj. With the current fork build, the BF16 mmproj can crash llama-server when several image requests run at once; Q80 is not affected and…
Read the full model card ↗ · Preview checked 2026-10-30T12:49:29.759Z
Inside the original model card — Document outline
- Bonsai 2 Ternary 9B: GGUF
- Highlights
- Model Overview
- Files
- Quickstart
- Use the PrismML llama.cpp build
- Text
- Image + text
- OpenAI-compatible server
- Best Practices
- Generation Parameters
- Output Length
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
prism-ml/Ternary-Bonsai-2-9B-gguf is a image-text-to-text model repository published by prism-ml on Hugging Face. The source reports the llama.cpp library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- llama.cpp
- Recent downloads (30 days)
- 104,143
- Cumulative likes
- 121
- Hugging Face trending score
- 84
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-23T06:12:31.000Z
- Last modified
- 2026-10-15T16:04:11.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.5-9B
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 2026-10-23T06:44:58.174Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.