LLM EXPLORER 66,613 MODELS INDEXED

Qwen3 Vl 2B Foveated Search Fp8 by honey613

By honey613 · 46 downloads
HF Repo ↗ Copy URL

Qwen3 Vl 2B Foveated Search Fp8 is an open-source language model by honey613. Features: 2b LLM, VRAM: 2.9GB, License: apache-2.0.

Base model:honey613/qwen3-vl-2... Base model:quantized:honey613/...   Compressed-tensors   Conversational   En   Endpoints compatible   Foveated   Fp8   Image-text-to-text   Llm-compressor   Qwen3-vl   Qwen3 vl   Region:us   Safetensors   Visual-search
Model Card on HF 🤗: https://huggingface.co/honey613/qwen3-vl-2b-foveated-search-fp8 

Qwen3 Vl 2B Foveated Search Fp8 Parameters and Internals

LLM NameQwen3 Vl 2B Foveated Search Fp8
Repository 🤗https://huggingface.co/honey613/qwen3-vl-2b-foveated-search-fp8 
Base Model(s)  Qwen3 Vl 2B Foveated Search   honey613/qwen3-vl-2b-foveated-search
Model Size2b
Required VRAM2.9 GB
Updated2026-11-04
Maintainerhoney613
Model Typeqwen3_vl
Model Files  2.9 GB
Supported Languagesen
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3 Vl 2B Foveated Search Fp8

Best Alternatives
Context / RAM
Downloads
Likes
WeVisOne VL 2B0K / 4.9 GB204939
Qwen3 VL 2B Instruct0K / 4.3 GB2204577448
Qwen3 VL Reranker 2B0K / 4.3 GB764323212
WeVisDoc 2B0K / 4.9 GB59914
Qwen3 VL 2B Thinking0K / 4.3 GB74744115
VIG Qwen3 VL Thinking 2B0K / 4.9 GB551
PhysBrain1.5 2B0K / 4.3 GB27213
...l 2B Medical Pmcvqa Sft Merged0K / 4.3 GB4060
Qwen3 VL 2B Instruct FP80K / 3.5 GB6506343
Typhoon Ocr1.5 2B0K / 4.3 GB5502925
Note: green Score (e.g. "73.2") means that the model is better than honey613/qwen3-vl-2b-foveated-search-fp8.