prism-ml/Ternary-Bonsai-2-27B-gguf
Full fine-tune vs Qwen/Qwen3.8-27B. prism-ml/Ternary-Bonsai-2-27B-gguf is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 161/161, MLP 192/192, Attention 64/64, Embeddings 1/1, lm_head 1/1
21 derivatives checked
- ProCreations/Ternary-Bonsai-2-27B-DFlash2: Not comparable yet
- fraserprice/Ternary-Bonsai-2-27B-vllm: Quantization
- decent-jawfish/bonsai-2-27b-mtp: Same weights, converted
- CaryPalmer/Ternary-Bonsai-2-27B-262k-GGUF: Same weights, converted
- pipenetwork/Ternary-Bonsai-2-27B-MLX-4bit: Quantization
- webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO: Quantization
- talxcc/Tals-coder-flash-02: Full fine-tune
- AtomicChat/Ternary-Bonsai-2-27B-Abliterate-LoRA-GGUF: Different architecture
- TokenAI-zer/Ternary-Bonsai-2-27B-MLX-oQ8-mtp: Quantization
- killy369/Ternary-Bonsai-2-27B-MTP-drafter-GGUF: Full fine-tune
- pipenetwork/Ternary-Bonsai-2-27B-MLX-8bit: Quantization
- pipenetwork/Ternary-Bonsai-2-27B-MLX-6bit: Quantization
- TokenAI-zer/Ternary-Bonsai-2-27B-MLX-oQ2-mtp: Quantization
- TokenAI-zer/Ternary-Bonsai-2-27B-MLX-oQ4-mtp: Quantization
- pipenetwork/Ternary-Bonsai-2-27B-MLX-bf16: Full fine-tune
- TokenAI-zer/Ternary-Bonsai-2-27B-MLX-oQ6-mtp: Quantization
- TokenAI-zer/Ternary-Bonsai-2-27B-MLX-oQ3-mtp: Quantization
- ManniX-ITA/Ternary-Bonsai-2-27B-MTP-GGUF: Same weights, converted
- xyznq1/xyz-drafter: Full fine-tune
- the-sweater-cat/bonsai-2-pq2: Quantization
- com-kotobalabs/Ternary-Bonsai-2-27B-Refusal-Steering-GGUF: Different architecture