Downloads · 30 days
299
20% of all-time downloads
jakeatx/Qwen3.8-27B-Ternary-PQ2_0-MTP-GGUF
Qwen3.8-27B-Ternary-PQ2_0-MTP-GGUF is a machine learning model from jakeatx. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
2-bit / 2.13 bpw ternary quantization of Qwen3.8-27B (Prism ML Ternary Bonsai 2 architecture) with native 1-layer MTP speculative drafting.
Downloads · 30 days
299
20% of all-time downloads
All-time downloads
1.5K
Public
Repo size
15.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf7.5 GB · 100%
From the Hugging Face model README
2-bit / 2.13 bpw ternary quantization of Qwen3.8-27B (Prism ML Ternary Bonsai 2 architecture) with native 1-layer MTP speculative drafting.
PQ2_0 (group 128, 34 bytes/block, ~2.13 bpw)feature/v0.3.1-bonsai2)./build-sm86/bin/llama-server \
-m Qwen3.8-27B-Ternary-PQ2_0-MTP.gguf \
-c 32768 -b 4096 -ub 1024 -t 8 -ngl 99 -fa on -ctk q8_0 -ctv turbo3 \
--spec-type draft-mtp --spec-draft-n-max 3 --spec-draft-p-min 0