Best Sub 2B model, Fit for SLM and Agentic Tasks
Susant Achary PRO
Susant-Achary
AI & ML interests
Building from India. Post Training ,Quantisation(GGUF,ONNX,MLX) Tiny to Small Language Models(Vision, Text, Audio),
Specialisation in Computer vision, Information Retrieval & Representation, Personalisation.(Healthcare Imaging, Geospatial, DocAI,Ecommerce)
Recent Activity
liked a model 5 days ago
facebook/MobileMoE-S-Base updated a collection 22 days ago
OpenBMB-2B liked a model 22 days ago
openbmb/MiniCPM5-2B-MLXOrganizations
the most powerful vision-language model in the Qwen series to date. Available in Dense and MoE architectures
-
Qwen/Qwen3-VL-30B-A3B-Thinking
Image-Text-to-Text • 31B • Updated • 17.9k • • 203 -
mlx-community/Qwen3-VL-30B-A3B-Instruct-4bit
Image-Text-to-Text • Updated • 1.39k • 9 -
mlx-community/Qwen3-VL-30B-A3B-Instruct-8bit
Image-Text-to-Text • Updated • 241 • 3 -
mlx-community/Qwen3-VL-8B-Instruct-4bit
Image-Text-to-Text • Updated • 7.4k • 9
Curated MLX-ready quantized LLMs that run fast on Apple Silicon (and some on iOS). Every card lists Bits · Group size · Peak UM (GB) · Stable context.
-
mlx-community/Apriel-1.5-15b-Thinker-3bit-MLX
Image-Text-to-Text • Updated • 33 -
mlx-community/Apriel-1.5-15b-Thinker-6bit-MLX
Image-Text-to-Text • Updated • 47 • 1 -
mlx-community/granite-4.0-h-tiny-3bit-MLX
Text Generation • 7B • Updated • 60 • 2 -
mlx-community/granite-4.0-tiny-preview-4bit
Text Generation • 7B • Updated • 79
-
facebook/dinov2-base
Image Feature Extraction • 86.6M • Updated • 2.92M • 202 -
openai/clip-vit-large-patch14-336
Zero-Shot Image Classification • Updated • 2.29M • 311 -
google/siglip-so400m-patch14-384
Zero-Shot Image Classification • 0.9B • Updated • 1.18M • 691 -
BAAI/EVA-CLIP-8B
Feature Extraction • Updated • 708 • 51
Models that turn a single image (or image+prompt) into 3D assets meshes, Gaussians, or point clouds suited for AR/VR, product turntables, game props.
open T2V & animation models emphasizing temporal coherence, controllability, and real-time playback. Great starting point for creative tools, Ads.
Free and Open Source provided you don't source model and claim right
-
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 3.99M • • 6.57k -
facebook/wav2vec2-base-960h
Automatic Speech Recognition • 94.4M • Updated • 1.71M • 406 -
openai/whisper-small
Automatic Speech Recognition • 0.2B • Updated • 3.25M • 611 -
openai/whisper-tiny
Automatic Speech Recognition • 37.8M • Updated • 1.01M • 452
Models that create short videos from written prompts. Perfect for experimentation in generative video and creative storytelling.
Image editing and transformation models :- from style transfer to super-resolution, inpainting, and diffusion-based edits.
-
stabilityai/stable-diffusion-xl-refiner-1.0
Image-to-Image • 2B • Updated • 99.4k • 2.07k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • 12B • Updated • 377k • • 2.87k -
Qwen/Qwen-Image-Edit
Image-to-Image • 20B • Updated • 109k • • 2.54k -
lllyasviel/sd-controlnet-canny
Image-to-Image • 0.4B • Updated • 26.6k • 252
Multimodal models that take image + text as input and produce natural language output. Use cases: chart QA, visual document reasoning, VQA.
-
Qwen/Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • 8B • Updated • 5.61M • • 1.73k -
Qwen/Qwen2.5-VL-3B-Instruct
Image-Text-to-Text • 4B • Updated • 2.28M • • 710 -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.24M • • 1.56k -
nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
Image-Text-to-Text • 9B • Updated • 84.7k • 181
Collection of top open LLMs for writing, summarization, chat, reasoning, and document drafting. Includes small SLMs for devices and large models .
Dataset that can 🌐chat, ⚡code and 🧮reasoning
MLX weights and proven for MLX inference
-
mlx-community/gpt-oss-20b-MXFP4-Q8
Text Generation • 21B • Updated • 245k • 96 -
lmstudio-community/Seed-OSS-36B-Instruct-MLX-4bit
Text Generation • 36B • Updated • 24.5k • 1 -
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-4bit
Text Generation • 4B • Updated • 44.8k • 14 -
mlx-community/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • 0.6B • Updated • 741k • 47
Tiny, fast models that run on iPhone/iPad or Mac with very low memory. Great for quick replies, offline note-assist, and routing
-
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bit
Text Generation • 4B • Updated • 43.9k • 8 -
lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit
Text Generation • 8B • Updated • 261k • 18 -
lmstudio-community/gemma-3n-E4B-it-MLX-4bit
Image-Text-to-Text • Updated • 31.8k • 4 -
mlx-community/gemma-3-4b-it-qat-4bit
Image-Text-to-Text • 5B • Updated • 48.5k • 9
The primary objective of project is to explore & analyze the impact of model size on text generation quality with GPT-2 arch trained from scratch.
Collection of Small size big impact MoE.
-
LiquidAI/LFM2-8B-A1B
Text Generation • 8B • Updated • 18.8k • 372 -
ibm-granite/granite-4.0-h-tiny
Text Generation • 7B • Updated • 58.8k • 210 -
microsoft/Phi-4-multimodal-instruct
Automatic Speech Recognition • 6B • Updated • 203k • 1.62k -
google/gemma-3n-E4B-it
Image-Text-to-Text • 8B • Updated • 12.7k • • 931
models for turning text, images, audio (and combos) into useful vectors or feature maps. Ideal for search/RAG, clustering, recommendation, retrieval.
coding models and pipelines released this month that boost repo-level reasoning, GUI automation, and tool use. Focused on practical editing.
Cutting-edge image generation & VLM updates from September ’25. This collection spotlights models that improved text rendering, layout control & more.
Speech synthesis models that turn text into natural audio. Includes multilingual TTS, low-latency real-time models, and voice-cloning variants.
State-of-the-art diffusion and generative models that turn text prompts into detailed images. Includes lightweight CPU-friendly and photorealistic mdl
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.61M • 1.3k -
stabilityai/stable-diffusion-xl-base-1.0
Text-to-Image • 3B • Updated • 4.37M • • 8.28k -
stabilityai/sd-turbo
Text-to-Image • 0.9B • Updated • 614k • 465 -
black-forest-labs/FLUX.1-dev
Text-to-Image • 12B • Updated • 698k • • 15.4k
OCR, captioning, and visual QA models that turn pure images into descriptive or structured text.
-
Salesforce/blip-image-captioning-base
Image-to-Text • Updated • 1.43M • 896 -
Salesforce/blip-image-captioning-large
Image-to-Text • 0.5B • Updated • 580k • 1.49k -
nlpconnect/vit-gpt2-image-captioning
Image-to-Text • Updated • 82.5k • 935 -
microsoft/trocr-base-handwritten
Image-to-Text • 0.3B • Updated • 179k • 523
Models that can flexibly convert across modalities (text, image, audio, video). Ideal for researchers exploring unified multimodal-AI.
Datasets tackling AI Toughest Challenges
10 CODING models that support ≥128k context (native or via officially documented scaling)
-
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 6.16M • • 8.26k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.24M • • 1.56k -
Qwen/Qwen3-Coder-30B-A3B-Instruct
Text Generation • 31B • Updated • 421k • • 1.27k -
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
Text Generation • 16B • Updated • 907k • 668
Best of Qwen3 Series of Models
-
Qwen/Qwen3-30B-A3B-Instruct-2507
Text Generation • 31B • Updated • 952k • • 841 -
Qwen/Qwen3-Next-80B-A3B-Thinking
Text Generation • 81B • Updated • 41.5k • • 496 -
Qwen/Qwen3-Coder-30B-A3B-Instruct
Text Generation • 31B • Updated • 421k • • 1.27k -
Qwen/Qwen3-Omni-30B-A3B-Instruct
Any-to-Any • 35B • Updated • 656k • 1.01k
Best Sub 2B model, Fit for SLM and Agentic Tasks
the most powerful vision-language model in the Qwen series to date. Available in Dense and MoE architectures
-
Qwen/Qwen3-VL-30B-A3B-Thinking
Image-Text-to-Text • 31B • Updated • 17.9k • • 203 -
mlx-community/Qwen3-VL-30B-A3B-Instruct-4bit
Image-Text-to-Text • Updated • 1.39k • 9 -
mlx-community/Qwen3-VL-30B-A3B-Instruct-8bit
Image-Text-to-Text • Updated • 241 • 3 -
mlx-community/Qwen3-VL-8B-Instruct-4bit
Image-Text-to-Text • Updated • 7.4k • 9
Collection of Small size big impact MoE.
-
LiquidAI/LFM2-8B-A1B
Text Generation • 8B • Updated • 18.8k • 372 -
ibm-granite/granite-4.0-h-tiny
Text Generation • 7B • Updated • 58.8k • 210 -
microsoft/Phi-4-multimodal-instruct
Automatic Speech Recognition • 6B • Updated • 203k • 1.62k -
google/gemma-3n-E4B-it
Image-Text-to-Text • 8B • Updated • 12.7k • • 931
Curated MLX-ready quantized LLMs that run fast on Apple Silicon (and some on iOS). Every card lists Bits · Group size · Peak UM (GB) · Stable context.
-
mlx-community/Apriel-1.5-15b-Thinker-3bit-MLX
Image-Text-to-Text • Updated • 33 -
mlx-community/Apriel-1.5-15b-Thinker-6bit-MLX
Image-Text-to-Text • Updated • 47 • 1 -
mlx-community/granite-4.0-h-tiny-3bit-MLX
Text Generation • 7B • Updated • 60 • 2 -
mlx-community/granite-4.0-tiny-preview-4bit
Text Generation • 7B • Updated • 79
-
facebook/dinov2-base
Image Feature Extraction • 86.6M • Updated • 2.92M • 202 -
openai/clip-vit-large-patch14-336
Zero-Shot Image Classification • Updated • 2.29M • 311 -
google/siglip-so400m-patch14-384
Zero-Shot Image Classification • 0.9B • Updated • 1.18M • 691 -
BAAI/EVA-CLIP-8B
Feature Extraction • Updated • 708 • 51
models for turning text, images, audio (and combos) into useful vectors or feature maps. Ideal for search/RAG, clustering, recommendation, retrieval.
Models that turn a single image (or image+prompt) into 3D assets meshes, Gaussians, or point clouds suited for AR/VR, product turntables, game props.
coding models and pipelines released this month that boost repo-level reasoning, GUI automation, and tool use. Focused on practical editing.
open T2V & animation models emphasizing temporal coherence, controllability, and real-time playback. Great starting point for creative tools, Ads.
Cutting-edge image generation & VLM updates from September ’25. This collection spotlights models that improved text rendering, layout control & more.
Free and Open Source provided you don't source model and claim right
-
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 3.99M • • 6.57k -
facebook/wav2vec2-base-960h
Automatic Speech Recognition • 94.4M • Updated • 1.71M • 406 -
openai/whisper-small
Automatic Speech Recognition • 0.2B • Updated • 3.25M • 611 -
openai/whisper-tiny
Automatic Speech Recognition • 37.8M • Updated • 1.01M • 452
Speech synthesis models that turn text into natural audio. Includes multilingual TTS, low-latency real-time models, and voice-cloning variants.
Models that create short videos from written prompts. Perfect for experimentation in generative video and creative storytelling.
State-of-the-art diffusion and generative models that turn text prompts into detailed images. Includes lightweight CPU-friendly and photorealistic mdl
-
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.61M • 1.3k -
stabilityai/stable-diffusion-xl-base-1.0
Text-to-Image • 3B • Updated • 4.37M • • 8.28k -
stabilityai/sd-turbo
Text-to-Image • 0.9B • Updated • 614k • 465 -
black-forest-labs/FLUX.1-dev
Text-to-Image • 12B • Updated • 698k • • 15.4k
Image editing and transformation models :- from style transfer to super-resolution, inpainting, and diffusion-based edits.
-
stabilityai/stable-diffusion-xl-refiner-1.0
Image-to-Image • 2B • Updated • 99.4k • 2.07k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • 12B • Updated • 377k • • 2.87k -
Qwen/Qwen-Image-Edit
Image-to-Image • 20B • Updated • 109k • • 2.54k -
lllyasviel/sd-controlnet-canny
Image-to-Image • 0.4B • Updated • 26.6k • 252
OCR, captioning, and visual QA models that turn pure images into descriptive or structured text.
-
Salesforce/blip-image-captioning-base
Image-to-Text • Updated • 1.43M • 896 -
Salesforce/blip-image-captioning-large
Image-to-Text • 0.5B • Updated • 580k • 1.49k -
nlpconnect/vit-gpt2-image-captioning
Image-to-Text • Updated • 82.5k • 935 -
microsoft/trocr-base-handwritten
Image-to-Text • 0.3B • Updated • 179k • 523
Multimodal models that take image + text as input and produce natural language output. Use cases: chart QA, visual document reasoning, VQA.
-
Qwen/Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • 8B • Updated • 5.61M • • 1.73k -
Qwen/Qwen2.5-VL-3B-Instruct
Image-Text-to-Text • 4B • Updated • 2.28M • • 710 -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.24M • • 1.56k -
nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1
Image-Text-to-Text • 9B • Updated • 84.7k • 181
Models that can flexibly convert across modalities (text, image, audio, video). Ideal for researchers exploring unified multimodal-AI.
Collection of top open LLMs for writing, summarization, chat, reasoning, and document drafting. Includes small SLMs for devices and large models .
Datasets tackling AI Toughest Challenges
Dataset that can 🌐chat, ⚡code and 🧮reasoning
10 CODING models that support ≥128k context (native or via officially documented scaling)
-
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 6.16M • • 8.26k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.24M • • 1.56k -
Qwen/Qwen3-Coder-30B-A3B-Instruct
Text Generation • 31B • Updated • 421k • • 1.27k -
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
Text Generation • 16B • Updated • 907k • 668
MLX weights and proven for MLX inference
-
mlx-community/gpt-oss-20b-MXFP4-Q8
Text Generation • 21B • Updated • 245k • 96 -
lmstudio-community/Seed-OSS-36B-Instruct-MLX-4bit
Text Generation • 36B • Updated • 24.5k • 1 -
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-4bit
Text Generation • 4B • Updated • 44.8k • 14 -
mlx-community/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • 0.6B • Updated • 741k • 47
Tiny, fast models that run on iPhone/iPad or Mac with very low memory. Great for quick replies, offline note-assist, and routing
-
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bit
Text Generation • 4B • Updated • 43.9k • 8 -
lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit
Text Generation • 8B • Updated • 261k • 18 -
lmstudio-community/gemma-3n-E4B-it-MLX-4bit
Image-Text-to-Text • Updated • 31.8k • 4 -
mlx-community/gemma-3-4b-it-qat-4bit
Image-Text-to-Text • 5B • Updated • 48.5k • 9
Best of Qwen3 Series of Models
-
Qwen/Qwen3-30B-A3B-Instruct-2507
Text Generation • 31B • Updated • 952k • • 841 -
Qwen/Qwen3-Next-80B-A3B-Thinking
Text Generation • 81B • Updated • 41.5k • • 496 -
Qwen/Qwen3-Coder-30B-A3B-Instruct
Text Generation • 31B • Updated • 421k • • 1.27k -
Qwen/Qwen3-Omni-30B-A3B-Instruct
Any-to-Any • 35B • Updated • 656k • 1.01k
The primary objective of project is to explore & analyze the impact of model size on text generation quality with GPT-2 arch trained from scratch.