No official torrent yet โ requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from dealignai/Bonsai-27b-Ternary-CRACK-GGUF
All models by dealignai โ
Vision-language ยท native Q2_0 ยท Prism llama.cpp
75.00% MMLU-200 logit ยท 99.38% full HB-320
Native Q2_0 GGUF release of the Bonsai 27B CRACK model for the Prism llama.cpp fork. This repo contains the quantized language model and the matching F16 Qwen3VL multimodal projector.
The projector contains 334 tensors and both temporal patch slices
v.patch_embd.weight and v.patch_embd.weight.1 (temporal_patch_size=2). The
original image and video processor configuration files are included. Image
input is live-tested. Direct video-container input depends on the Prism runtime
surface; extract frames or use a compatible Qwen3VL video client when the CLI
does not accept the container directly. See preprocessor_config.json and
video_preprocessor_config.json for the retained preprocessing metadata.
These native low-bit types require the Prism fork:
Text:
Image/VL:
Server:
MMLU is the same fixed, stratified 200-question sample for all rows. It uses next-token A/B/C/D logits with reasoning/thinking disabled; it is not a claim for the complete official MMLU suite. HB is the complete unsliced 320-case text run. The live text smoke measured 43.74โ44.10 tok/s and the image request measured 44.08 tok/s on an Apple M5 Max using the Prism Metal runtime.
qwen35 GGUF architecture)LICENSE.txt and NOTICE.txt์ด ์ ์ฅ์๋ Bonsai 27B CRACK ๋ชจ๋ธ์ ๋ค์ดํฐ๋ธ Q2_0 GGUF ๋ฐฐํฌ๋ณธ์ ๋๋ค. Prism llama.cpp ํฌํฌ๊ฐ ํ์ํ๋ฉฐ, ํ ์คํธ ๋ชจ๋ธ๊ณผ F16 Qwen3VL ๋ฉํฐ๋ชจ๋ฌ ํ๋ก์ ํฐ๋ฅผ ํจ๊ป ์ ๊ณตํฉ๋๋ค. ์ MMLU ์ ์๋ ์ถ๋ก ์ ๋ 200๋ฌธํญ ๋ก์ง ํ๊ฐ์ด๊ณ , HB ์ ์๋ ์ ์ฒด 320๋ฌธํญ ๊ฒฐ๊ณผ์ ๋๋ค. ์ด๋ฏธ์ง ์ ๋ ฅ์ ์ค์ ๋ก ๊ฒ์ฆํ์ผ๋ฉฐ ๋น๋์ค ์ปจํ ์ด๋ ์ ๋ ฅ์ ์ฌ์ฉ ์ค์ธ Prism ํด๋ผ์ด์ธํธ์ ์ง์ ์ฌ๋ถ๋ฅผ ํ์ธํด์ผ ํฉ๋๋ค.
git clone https://github.com/PrismML-Eng/llama.cppcd llama.cppcmake -B build && cmake --build build -j./build/bin/llama-cli \ -m Bonsai-27b-Ternary-CRACK-Q2_0.gguf \ --reasoning off -ngl 99 -n 256 \ -p "Explain quantum computing in simple terms."./build/bin/llama-cli \ -m Bonsai-27b-Ternary-CRACK-Q2_0.gguf \ --mmproj mmproj-Bonsai-27b-Ternary-CRACK-F16.gguf \ --image image.jpg --reasoning off -ngl 99 -n 256 \ -p "Describe the image precisely."./build/bin/llama-server \ -m Bonsai-27b-Ternary-CRACK-Q2_0.gguf \ --mmproj mmproj-Bonsai-27b-Ternary-CRACK-F16.gguf \ --reasoning off --host 0.0.0.0 --port 8080 -ngl 99