LiquidAI/LFM2.5-230M
Full fine-tune vs LiquidAI/LFM2.5-230M-Base. Fine-tune: 100% of the weights changed, across 14 of 14 layers.
Tensors changed: Embeddings 2/2, other 24/24, MLP 42/42, Norms 40/40, Attention 24/24
35 derivatives checked
- LiquidAI/LFM2.5-230M-GGUF: Full fine-tune
- unsloth/LFM2.5-230M-GGUF: Same weights, converted
- unsloth/LFM2.5-230M: Identical copy
- LiquidAI/LFM2.5-230M-MLX-4bit: Quantization
- Null-Guard/LFM2.5-230M-distilled-Gemini-3.8-Flash: Partial fine-tune
- Null-Guard/LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored: Partial fine-tune
- mradermacher/LFM2.5-230M-i1-GGUF: Quantization
- prithivMLmods/LiquidAI-LFM2.5-230M-GGUF: Same weights, converted
- LiquidAI/LFM2.5-230M-MLX-8bit: Quantization
- lugman-madhiai/LFM2.5-230M-SearchAgent-SFT-02: LoRA-style
- agentlans/LFM2.5-230M-Propella: Partial fine-tune
- Null-Guard/LFM2.5-230M-Uncensored-GGUF: Abliterated
- Flolep2607/grpo-product-search-lfm: Full fine-tune
- mradermacher/LFM2.5-230M-GGUF: Same weights, converted
- MarshallHD/LFM2.5-230M-NVFP4: Quantization
- lazos/lfm2.5-230m-frontend-agent: Full fine-tune
- DuoNeural/LFM2.5-230M-GTAP-v3-GGUF: Quantization
- trymirai/LFM2.5-230M-M: Quantization
- Indexnusrefather/Super-Slop-Machina-Macro-Roleplay-Instruct-230M-2608-Lobotomized: Full fine-tune
- trymirai/LFM2.5-230M-L: Quantization
- ManhHoDinh/lfm25-titlegen-curriculum: Partial fine-tune
- LiquidAI/LFM2.5-230M-MLX-bf16: Same weights, repacked
- ManhHoDinh/lfm25-titlegen-17-languages: Partial fine-tune
- AKMESSI/lfm2.5-230m-fable-5: LoRA-style
- ManhHoDinh/lfm25-titlegen-dpo: Partial fine-tune
- ManhHoDinh/lfm25-titlegen-sft: Partial fine-tune
- LiquidAI/LFM2.5-230M-MLX-6bit: Quantization
- LiquidAI/LFM2.5-230M-MLX-5bit: Quantization
- nwtgck/LFM2.5-230M-GGUF: Full fine-tune
- yrrhall/LFM2.5-230M-GGUF: Full fine-tune
5 other repos hold byte-for-byte identical weight files.