SmolVLM-Instruct-GGUF

Home/Models/Mungert/SmolVLM-Instruct-GGUF

Mungert/SmolVLM-Instruct-GGUF

kind: gguf
quant: gguf (16-bit)
family: smol
modality: image-text-to-text
root model: HuggingFaceTB/SmolLM2-1.7B-Instruct
provider: Mungert
license: apache-2.0
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 96
likes: 2
created: —
last modified: 2025-09-24T15:42:57+00:00 (2025)
huggingface: https://huggingface.co/Mungert/SmolVLM-Instruct-GGUF
tags: transformersggufimage-text-to-textendataset:HuggingFaceM4/the_cauldrondataset:HuggingFaceM4/Docmatixarxiv:2504.05299base_model:HuggingFaceTB/SmolLM2-1.7B-Instructbase_model:quantized:HuggingFaceTB/SmolLM2-1.7B-Instructlicense:apache-2.0endpoints_compatibleregion:usconversational

benchmark	category	score	conf	evidence
DocVQA	multimodal	81.6	high	`\| SmolVLM \| 38.8 \| 44.6 \| 42.1 \| 81.6 \| 72.7 \| 5.02 \|`
MathVista	multimodal	44.6	high	`\| SmolVLM \| 38.8 \| 44.6 \| 42.1 \| 81.6 \| 72.7 \| 5.02 \|`
MMMU	multimodal	38.8	high	`\| SmolVLM \| 38.8 \| 44.6 \| 42.1 \| 81.6 \| 72.7 \| 5.02 \|`

none scraped.