LiquidAI/LFM2.5-2.6B
Full fine-tune vs LiquidAI/LFM2.5-2.6B-Base. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 2/2, other 66/66, MLP 90/90, Norms 76/76, Attention 32/32
113 derivatives checked
- LiquidAI/LFM2.5-2.6B-GGUF: Same weights, converted
- DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF: Same weights, converted
- LiquidAI/LFM2.5-2.6B-DSpark: Different architecture
- KridgeDookie/LFM2.5-2.6B-UNCENSORED-ABLITERATED-PHILADELPHIA-CLASS: Abliterated
- lmstudio-community/LFM2.5-2.6B-MLX-8bit: Quantization
- bartowski/LiquidAI_LFM2.5-2.6B-GGUF: Same weights, converted
- Davd-b01/lfm2.5-2.6B-thinkingcap-distiller-v2: Partial fine-tune
- Abiray/LFM2.5-2.6B-Heretic-Abliterated-GGUF: Quantization
- SC117/LFM2.5-2.6B-Uncensored-GGUF: Abliterated
- LiquidAI/LFM2.5-2.6B-MLX-8bit: Quantization
- zaakirio/LFM2.5-2.6B-Uncensored-GGUF: Abliterated
- nassimjp/LFM2.5-2.6B-Pashto-Zi: Same weights, repacked
- reaperdoesntknow/LFM2.5-2.6B-CyberSec: Quantization
- mlx-community/LFM2.5-2.6B-4bit: Quantization
- LiquidAI/LFM2.5-2.6B-MLX-4bit: Quantization
- atakankutalp/LFM2.5-2.6B-heretic: Abliterated
- mradermacher/LFM2.5-2.6B-i1-GGUF: Quantization
- KittyLM/kittylm-lfm2.5-2.6b: Partial fine-tune
- netgoat-ai/koda-ids-frontier: LoRA-style
- bunnycore/LMF-2.5-2B-Code-GGUF: Quantization
- lmstudio-community/LFM2.5-2.6B-MLX-4bit: Quantization
- NANI-Nithin/LFM2.5-2.6B-GGUF: Same weights, converted
- lmstudio-community/LFM2.5-2.6B-GGUF: Quantization
- SC117/LFM2.5-2.6B-Uncensored: Abliterated
- monotykamary/LFM2.5-2.6B-RLCD: Identical copy
- Davd-b01/lfm2.5-2.6B-thinkingcap-distiller: Partial fine-tune
- KikoCis/LFM2.5-2.6B-GGUF: Quantization
- Schnuckade/LFM-2.5-Coder-2.6B: LoRA-style
- noctrex/LFM2.5-2.6B-heretic-uncensored-GGUF: Abliterated
- mradermacher/LFM2.5-2.6B-GGUF: Same weights, converted
6 other repos hold byte-for-byte identical weight files.