Updated daily through an automated data pipeline FNI Ranked
The Open-Source AI Registry
Discover and rank 580,000+ models, datasets, papers, and tools. Scored by the Free2AITools Nexus Index (FNI).
No models found.
Try a different search term.
Browse by category
π¬
Text Generation
Core LLMs, code assistants, and reasoning engines.
Browse β
π
Knowledge Retrieval
Embeddings, RAG components, and semantic search.
Browse β
π¨
Vision & Multimedia
Diffusion, video processing, and audio synthesis.
Browse β
β‘
Automation & Workflow
Agents, task-specific pipelines, and orchestration.
Browse β
π§
Infrastructure
Quantization, serving stacks, and optimization.
Browse β
Top FNI-ranked entries
Ranked by FNI
Error:
image text to text
gemma-4-26B-A4B-it-FP8-Dynamic
ARCH: Gemma4ForConditionalGeneration
π§ 26.56B Size
π 8k CTX
πΎ ~21.2G VRAM
π Apache License
π₯ 1.5M DL
62 FNI
image text to text
gemma-4-26B-A4B-it-NVFP4
ARCH: Gemma4ForConditionalGeneration
π§ 15.09B Size
π 8k CTX
πΎ ~12.6G VRAM
π Apache License
π₯ 1.1M DL
62 FNI
image text to text
gemma-4-31B-it-FP8-Dynamic
ARCH: Gemma4ForConditionalGeneration
π§ 32.68B Size
π 8k CTX
πΎ ~27G VRAM
π Apache License
π₯ 226K DL
60 FNI
model
Qwen3.6-27B-GGUF
ARCH: model
π§ 27B Size
πΎ ~21.6G VRAM
π Apache License
π₯ 330K DL
59 FNI
image text to text
Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic
ARCH: Mistral3ForConditionalGeneration
π§ 24.01B Size
π 33k CTX
πΎ ~20.5G VRAM
π Apache License
π₯ 80K DL
59 FNI
text generation
Qwen3.6-27B-MTPLX-Optimized-Speed
ARCH: Qwen3_5ForConditionalGeneration
π§ 4.67B Size
π 33k CTX
πΎ ~6G VRAM
π Apache License
π₯ 45K DL
58 FNI
image text to text
NuExtract-2.0-8B-GPTQ
ARCH: Qwen2_5_VLForConditionalGeneration
π§ 8.29B Size
π 33k CTX
πΎ ~8.7G VRAM
π MIT License
π₯ 172K DL
58 FNI
text generation
Qwen3-0.6B
ARCH: text generation
π§ 0.6B Size
πΎ ~1.8G VRAM
π Apache License
π₯ 22K DL
58 FNI
image text to text
Qwen3.6-27B-4bit
ARCH: Qwen3_5ForConditionalGeneration
π§ 4.67B Size
π 33k CTX
πΎ ~6G VRAM
π Apache License
π₯ 40K DL
58 FNI
image text to text
Kimi-K2.7-Code
ARCH: KimiK25ForConditionalGeneration
πΎ ~796.4G VRAM
π Other License
π₯ 448K DL
58 FNI
text generation
Llama-3.3-70B-Instruct-quantized.w8a8
ARCH: LlamaForCausalLM
π§ 70.56B Size
π 8k CTX
πΎ ~55.4G VRAM
π llama3.3 License
π₯ 17K DL
58 FNI
model
gemma-4-19b-a4b-it-REAP-i1-GGUF
ARCH: model
π§ 19B Size
πΎ ~15.6G VRAM
π Gemma License
π₯ 10K DL
57 FNI