SmolVLM-256M-Instruct-GGUF

Home/Models/Mungert/SmolVLM-256M-Instruct-GGUF

Mungert/SmolVLM-256M-Instruct-GGUF

kind: gguf
quant: gguf (16-bit)
family: smol
modality: image-text-to-text
root model: HuggingFaceTB/SmolLM2-135M-Instruct
provider: Mungert
license: apache-2.0
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 112
likes: 0
created: —
last modified: 2025-09-24T15:43:00+00:00 (2025)
huggingface: https://huggingface.co/Mungert/SmolVLM-256M-Instruct-GGUF
tags: transformersggufimage-text-to-textendataset:HuggingFaceM4/the_cauldrondataset:HuggingFaceM4/Docmatixarxiv:2504.05299base_model:HuggingFaceTB/SmolLM2-135M-Instructbase_model:quantized:HuggingFaceTB/SmolLM2-135M-Instructlicense:apache-2.0endpoints_compatibleregion:usconversational

benchmark	category	score	conf	evidence
DocVQA	multimodal	58.3	high	`\| 256M \| 35.9 \| 28.3 \| 52.6 \| 34.6 \| 47 \| 55.8 \| 73.6 \| 49.9 \| 58.3 \|`
ChartQA	multimodal	55.8	high	`\| 256M \| 35.9 \| 28.3 \| 52.6 \| 34.6 \| 47 \| 55.8 \| 73.6 \| 49.9 \| 58.3 \|`
MathVista	multimodal	35.9	high	`\| 256M \| 35.9 \| 28.3 \| 52.6 \| 34.6 \| 47 \| 55.8 \| 73.6 \| 49.9 \| 58.3 \|`
MMMU	multimodal	28.3	high	`\| 256M \| 35.9 \| 28.3 \| 52.6 \| 34.6 \| 47 \| 55.8 \| 73.6 \| 49.9 \| 58.3 \|`

none scraped.