LFM2.5-VL-1.6B-GGUF

Home/Models/unsloth/LFM2.5-VL-1.6B-GGUF

unsloth/LFM2.5-VL-1.6B-GGUF

kind: gguf
quant: gguf (16-bit)
family: misc
modality: image-text-to-text
root model: LiquidAI/LFM2.5-VL-1.6B
provider: unsloth
license: other
language: en, ja, ko, fr, es, de, ar, zh
context: 32,768
library: transformers
vRAM (GB): —
size on disk: —
downloads: 3,259
likes: 27
created: —
last modified: 2026-01-10T06:37:51+00:00 (2026)
huggingface: https://huggingface.co/unsloth/LFM2.5-VL-1.6B-GGUF
tags: transformersggufliquidunslothlfm2lfm2-vledgelfm2.5-vllfm2.5image-text-to-textenjakofresdearzharxiv:2511.23404base_model:LiquidAI/LFM2.5-VL-1.6Bbase_model:quantized:LiquidAI/LFM2.5-VL-1.6Blicense:otherendpoints_compatibleregion:us

benchmark	category	score	conf	evidence
MMBench	multimodal	65.9	low	`\| LFM2.5-VL-1.6B \| 50.67 \| 52.29 \| 48.82 \| 62.71 \| 41.44 \| 64.84 \| 40.56 \| 76.96 \| 65.90 \|`
IFEval	instruction-following	52.29	low	`\| LFM2.5-VL-1.6B \| 50.67 \| 52.29 \| 48.82 \| 62.71 \| 41.44 \| 64.84 \| 40.56 \| 76.96 \| 65.90 \|`
MMMU	multimodal	40.56	low	`\| LFM2.5-VL-1.6B \| 50.67 \| 52.29 \| 48.82 \| 62.71 \| 41.44 \| 64.84 \| 40.56 \| 76.96 \| 65.90 \|`

none scraped.