Task-Specific Fine-Tunes — FFT, LoRA & QLoRA Parameter-efficient fine-tunes across three base families (Qwen2.5, Llama 3.2, Gemma 3) at 1B–3B scale. Text-to-SQL, reflective reasoning, paraphrasin Collection by emonHasan01 Oct 17 - emonHasan01/qwen2.5-3b-text2sql Text Generation • 3B • Updated Oct 15 • 412 • 6 emonHasan01/llama-3.2-3b-reflect Text Generation • 3B • Updated Oct 15 • 834 • 7 emonHasan01/gemma-3-1b-paraphrase Text Generation • 1B • Updated Oct 15 • 610 • 6 emonHasan01/qwen2.5-3b-dialogsum-qlora Summarization • Updated Oct 14 • 15
AstroAgentBench An agent benchmark on space mission design tasks: paper, RL environments, traces and an interactive space Collection by kaupane Oct 17 - kaupane/AstroAgentBench RL Environment • Updated Oct 17 • 101 • 692 AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems Paper • 2601.11354 • Published Jan 16 • 5 kaupane/AstroAgentBench-Traces Traces • Updated Oct 17 • 115 • 254
AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems Paper • 2601.11354 • Published Jan 16 • 5
wan14b Collection by technigator Oct 17 - Running on Zero MCP 45 Wan2.2 14B Fast Preview 🐌 45 generate a video from an image with a text prompt
Running on Zero MCP 45 Wan2.2 14B Fast Preview 🐌 45 generate a video from an image with a text prompt
laya-indic 322M zero-shot typed-decision model for Indian languages + Hinglish, and its open training data (real Sangraha text + synthetic, Qwen3-labelled). Collection by LatentAILabs Oct 17 1 LatentAILabs/laya-indic Text Classification • 0.3B • Updated 13 days ago • 136 • 3 LatentAILabs/laya-indic-real-text Viewer • Updated 13 days ago • 24k • 179 • 1 LatentAILabs/laya-indic-synthetic Viewer • Updated 13 days ago • 62.3k • 250 • 1
General Collection by Slivy Oct 17 - google/gemma-4-E2B-it-qat-w4a16-ct Any-to-Any • 6B • Updated Jul 20 • 341k • 20
Bangla LLM Suite — Fine-tuned, Quantized & Deployed End-to-end Bangla language models: Generation and summarization checkpoints, each shipped with quantized GGUF or ONNX builds and a live demo Sp Collection by emonHasan01 Oct 17 - emonHasan01/BanglaGPT-Pro Text Generation • 1.0B • Updated 23 days ago • 1.25k • 6 emonHasan01/Bangla-Gemma-Pro Text Generation • 0.9B • Updated about 1 month ago emonHasan01/bangla-summarizer-pro Summarization • 1B • Updated Oct 17 • 50 • 6 emonHasan01/BanglaGPT-Pro-ONNX Text Generation • Updated about 1 month ago • 116
8gb Collection by jstealth 16 days ago - llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF Any-to-Any • 8B • Updated about 1 hour ago • 147k • 329 HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive 9B • Updated Jun 5 • 643k • 2.55k mradermacher/Qwen3.5-9B-The-Defiant-Fable-DARK-ROAST-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF 9B • Updated Oct 9 • 3.87k • 4
llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF Any-to-Any • 8B • Updated about 1 hour ago • 147k • 329
mradermacher/Qwen3.5-9B-The-Defiant-Fable-DARK-ROAST-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF 9B • Updated Oct 9 • 3.87k • 4
QWEN/Claude Collection by XCOM79 Oct 17 - DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED Image-Text-to-Text • 9B • Updated 11 days ago • 658 • 60
DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED Image-Text-to-Text • 9B • Updated 11 days ago • 658 • 60
Claes Danish decision (aka system one) models. Collection by syvai Oct 17 - syvai/claes-preview 0.3B • Updated Oct 4 • 16 • 2
Task-Specific Fine-Tunes — FFT, LoRA & QLoRA Parameter-efficient fine-tunes across three base families (Qwen2.5, Llama 3.2, Gemma 3) at 1B–3B scale. Text-to-SQL, reflective reasoning, paraphrasin Collection by emonHasan01 Oct 17 - emonHasan01/qwen2.5-3b-text2sql Text Generation • 3B • Updated Oct 15 • 412 • 6 emonHasan01/llama-3.2-3b-reflect Text Generation • 3B • Updated Oct 15 • 834 • 7 emonHasan01/gemma-3-1b-paraphrase Text Generation • 1B • Updated Oct 15 • 610 • 6 emonHasan01/qwen2.5-3b-dialogsum-qlora Summarization • Updated Oct 14 • 15
General Collection by Slivy Oct 17 - google/gemma-4-E2B-it-qat-w4a16-ct Any-to-Any • 6B • Updated Jul 20 • 341k • 20
AstroAgentBench An agent benchmark on space mission design tasks: paper, RL environments, traces and an interactive space Collection by kaupane Oct 17 - kaupane/AstroAgentBench RL Environment • Updated Oct 17 • 101 • 692 AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems Paper • 2601.11354 • Published Jan 16 • 5 kaupane/AstroAgentBench-Traces Traces • Updated Oct 17 • 115 • 254
AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems Paper • 2601.11354 • Published Jan 16 • 5
Bangla LLM Suite — Fine-tuned, Quantized & Deployed End-to-end Bangla language models: Generation and summarization checkpoints, each shipped with quantized GGUF or ONNX builds and a live demo Sp Collection by emonHasan01 Oct 17 - emonHasan01/BanglaGPT-Pro Text Generation • 1.0B • Updated 23 days ago • 1.25k • 6 emonHasan01/Bangla-Gemma-Pro Text Generation • 0.9B • Updated about 1 month ago emonHasan01/bangla-summarizer-pro Summarization • 1B • Updated Oct 17 • 50 • 6 emonHasan01/BanglaGPT-Pro-ONNX Text Generation • Updated about 1 month ago • 116
8gb Collection by jstealth 16 days ago - llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF Any-to-Any • 8B • Updated about 1 hour ago • 147k • 329 HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive 9B • Updated Jun 5 • 643k • 2.55k mradermacher/Qwen3.5-9B-The-Defiant-Fable-DARK-ROAST-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF 9B • Updated Oct 9 • 3.87k • 4
llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF Any-to-Any • 8B • Updated about 1 hour ago • 147k • 329
mradermacher/Qwen3.5-9B-The-Defiant-Fable-DARK-ROAST-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF 9B • Updated Oct 9 • 3.87k • 4
wan14b Collection by technigator Oct 17 - Running on Zero MCP 45 Wan2.2 14B Fast Preview 🐌 45 generate a video from an image with a text prompt
Running on Zero MCP 45 Wan2.2 14B Fast Preview 🐌 45 generate a video from an image with a text prompt
QWEN/Claude Collection by XCOM79 Oct 17 - DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED Image-Text-to-Text • 9B • Updated 11 days ago • 658 • 60
DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED Image-Text-to-Text • 9B • Updated 11 days ago • 658 • 60
laya-indic 322M zero-shot typed-decision model for Indian languages + Hinglish, and its open training data (real Sangraha text + synthetic, Qwen3-labelled). Collection by LatentAILabs Oct 17 1 LatentAILabs/laya-indic Text Classification • 0.3B • Updated 13 days ago • 136 • 3 LatentAILabs/laya-indic-real-text Viewer • Updated 13 days ago • 24k • 179 • 1 LatentAILabs/laya-indic-synthetic Viewer • Updated 13 days ago • 62.3k • 250 • 1
Claes Danish decision (aka system one) models. Collection by syvai Oct 17 - syvai/claes-preview 0.3B • Updated Oct 4 • 16 • 2