No machine on this network has measured this model yet. Everything below is what the catalog knows exists — where the weights come from, how large each build is, and whose work it is. Nothing here is a claim about what the model can do; that only appears once a machine has run it and signed the result.
hf.co/unsloth/LFM2.5-24B-A2B-GGUF:IQ2_XXSollama · IQ2_XXS · 7.0 GiB · quantizer (unsloth)
hf.co/unsloth/LFM2.5-24B-A2B-GGUF:IQ2_Mollama · IQ2_M · 7.0 GiB · quantizer (unsloth)
hf.co/unsloth/LFM2.5-24B-A2B-GGUF:IQ3_XXSollama · IQ3_XXS · 8.3 GiB · quantizer (unsloth)
LiquidAI/LFM2.5-24B-A2B-MLX-4bitmlx · 4BIT · 12.6 GiB · vendor (LiquidAI)
hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q4_0ollama · Q4_0 · 12.6 GiB · vendor (LiquidAI)
hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q4_K_Mollama · Q4_K_M · 13.5 GiB · vendor (LiquidAI)
LiquidAI/LFM2.5-24B-A2B-MLX-5bitmlx · 5BIT · 15.4 GiB · vendor (LiquidAI)
LiquidAI/LFM2.5-24B-A2B-FP8vllm · FP8 · 23.0 GiB · vendor (LiquidAI)
LiquidAI/LFM2.5-24B-A2B-MLX-8bitmlx · 8BIT · 23.7 GiB · vendor (LiquidAI)
hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:Q8_0ollama · Q8_0 · 23.7 GiB · vendor (LiquidAI)
LiquidAI/LFM2.5-24B-A2Bvllm · BF16 · 44.7 GiB · vendor (LiquidAI)
LiquidAI/LFM2.5-24B-A2B-MLX-bf16mlx · BF16 · 44.7 GiB · vendor (LiquidAI)
hf.co/LiquidAI/LFM2.5-24B-A2B-GGUF:BF16ollama · BF16 · 44.7 GiB · vendor (LiquidAI)