LiquidAI/LFM2.5-8B-A1B
Full fine-tune vs LiquidAI/LFM2.5-8B-A1B-Base. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: MLP 2162/2162, Embeddings 2/2, other 54/54, Norms 60/60, Attention 24/24
69 derivatives checked
- LiquidAI/LFM2.5-8B-A1B-GGUF: Same weights, converted
- unsloth/LFM2.5-8B-A1B-GGUF: Same weights, converted
- DavidAU/LFM2.5-8B-A1B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF: Same weights, converted
- gaston-parravicini/LFM2.5-8B-A1B-Uncensored-Gaston-GGUF: Quantization
- AlexAtomic/lfm25-8b-a1b-GGUF: Quantization
- reaperdoesntknow/LFM2.5-8B-A1B-Opus-Distil: Partial fine-tune
- mudler/LFM2.5-8B-A1B-APEX-GGUF: Quantization
- LiquidAI/LFM2.5-8B-A1B-MLX-4bit: Quantization
- mlx-community/LFM2.5-8B-A1B-MLX-4bit: Quantization
- virtuanista/LFM2.5-8B-A1B-Uncensored-GGUF: Quantization
- LiquidAI/LFM2.5-8B-A1B-MLX-8bit: Quantization
- LiquidAI/LFM2.5-8B-A1B-DSpark: Different architecture
- Justbackup/LFM2.5-8B-A1B-Uncensored-Gaston-GGUF: Quantization
- saidutta69/LFM2.5-8B-A1B-heretic: Abliterated
- RemySkye/LFM2.5-8B-A1B-i1-GGUF: Same weights, converted
- Susant-Achary/LFM2.5-8B-A1B-UltraCoder-L3: Full fine-tune
- cyankiwi/LFM2.5-8B-A1B-AWQ-INT4: Quantization
- AtomicChat/LFM2.5-8B-A1B-GGUF: Quantization
- unsloth/LFM2.5-8B-A1B: Identical copy
- PocketAiHub/LFM2.5-8B-A1B-Abliterated: Quantization
- DuoNeural/LFM2.5-8B-A1B-TAP-DPQ-v7-GGUF: Quantization
- mlx-community/LFM2.5-8B-A1B-OptiQ-4bit: Quantization
- sakamakismile/LFM2.5-8B-A1B-NVFP4: Quantization
- w-ahmad/LFM2.5-8B-A1B-GGUF-MoQ: Same weights, converted
- LiquidAI/LFM2.5-8B-A1B-MLX-6bit: Quantization
- exeterminal/Exe-Turbo-S-V3-GGUF: Partial fine-tune
- sahilchachra/LFM2.5-8B-A1B-Uncensored: Full fine-tune
- huihui-ai/Huihui-LFM2.5-8B-A1B-abliterated: Abliterated
- jakeatx/LFM-2.5-8B-1B-hermes-ft: Quantization
- DhruvalLabs/LFM2.5-8B-A1B-GGUF: Quantization
11 other repos hold byte-for-byte identical weight files.