Text to Video Collection by hakuryv Aug 15 - MiniMaxAI/MiniMax-H3 Image-Text-to-Video • 33B • Updated about 11 hours ago • 5.75M • • 7.24k
Any To Any Collection by krubn Aug 15 - google/gemma-4-E4B-it-qat-q4_0-gguf Any-to-Any • 7B • Updated Jul 17 • 1.17M • 202
Science CoT Datasets Collection by moonlightprolove Aug 15 - allenai/ai2_arc Viewer • Updated Dec 21, 2023 • 7.79k • 534k • 433 stemdataset/STEM Viewer • Updated Apr 30, 2024 • 1.07M • 1.13k • 6
Uncensored Collection by Kemovi Aug 15 - HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive Image-Text-to-Text • 27B • Updated Apr 24 • 61.4k • 752 Shar514/Flux-Uncensored-V2 Image-to-Image • Updated May 11 • 25.3k • 48
HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive Image-Text-to-Text • 27B • Updated Apr 24 • 61.4k • 752
🔥 Qwen 3.8 — Newest 27B, Korean-verified Qwen's newest 27B: vision, 262K context, Korean-verified. Start with IQ4_XS — we measured every tier and Q3_K_M is smaller yet slower. Needs 24GB+. Collection by batiai Aug 16 1 batiai/Qwen3.8-27B-GGUF Text Generation • 27B • Updated Aug 27 • 1.15k • 2 batiai/Qwen3.6-35B-A3B-GGUF Text Generation • 35B • Updated May 4 • 1.16k • 6 batiai/Qwen3.6-27B-GGUF Text Generation • 27B • Updated Aug 16 • 32.2k • 8
Instruction Datasets Collection by moonlightprolove Aug 15 - livebench/instruction_following Viewer • Updated Apr 7, 2025 • 400 • 10.7k • 8
Code CoT Datasets Collection by moonlightprolove Sep 1 - livebench/coding Viewer • Updated Apr 7, 2025 • 128 • 6.56k • 14 openai/openai_humaneval Viewer • Updated Jan 4, 2024 • 164 • 292k • 419
Vyom TTS Vyom TTS is released as part of OpenXFI, an open-source Indic AI initiative by ATX Labs. Collection by atx-labs Aug 15 3 atx-labs/Vyom-TTS-Marathi-3B Text-to-Speech • 3B • Updated Oct 12 • 6 • 2 atx-labs/Vyom-TTS-Hindi-3B Text-to-Speech • 3B • Updated Oct 12 • 27 • 2
Qwen3.8-27B — MLX, multimodal preserved Qwen3.8-27B for Apple silicon — vision tower (333 tensors, bf16) and vendor MTP head both preserved and verified. 8-bit / 6-bit / 4-bit AWQ. Collection by avlp12 Aug 16 2 avlp12/Qwen3.8-27B-Alis-MLX-8bit Image-Text-to-Text • 27B • Updated Aug 22 • 373 • 9 avlp12/Qwen3.8-27B-Alis-MLX-6bit Image-Text-to-Text • 27B • Updated Aug 22 • 161 • 1 avlp12/Qwen3.8-27B-Alis-MLX-4bit Image-Text-to-Text • 27B • Updated Aug 22 • 233 • 4
Text to Video Collection by hakuryv Aug 15 - MiniMaxAI/MiniMax-H3 Image-Text-to-Video • 33B • Updated about 11 hours ago • 5.75M • • 7.24k
Instruction Datasets Collection by moonlightprolove Aug 15 - livebench/instruction_following Viewer • Updated Apr 7, 2025 • 400 • 10.7k • 8
Any To Any Collection by krubn Aug 15 - google/gemma-4-E4B-it-qat-q4_0-gguf Any-to-Any • 7B • Updated Jul 17 • 1.17M • 202
Code CoT Datasets Collection by moonlightprolove Sep 1 - livebench/coding Viewer • Updated Apr 7, 2025 • 128 • 6.56k • 14 openai/openai_humaneval Viewer • Updated Jan 4, 2024 • 164 • 292k • 419
Science CoT Datasets Collection by moonlightprolove Aug 15 - allenai/ai2_arc Viewer • Updated Dec 21, 2023 • 7.79k • 534k • 433 stemdataset/STEM Viewer • Updated Apr 30, 2024 • 1.07M • 1.13k • 6
Vyom TTS Vyom TTS is released as part of OpenXFI, an open-source Indic AI initiative by ATX Labs. Collection by atx-labs Aug 15 3 atx-labs/Vyom-TTS-Marathi-3B Text-to-Speech • 3B • Updated Oct 12 • 6 • 2 atx-labs/Vyom-TTS-Hindi-3B Text-to-Speech • 3B • Updated Oct 12 • 27 • 2
Uncensored Collection by Kemovi Aug 15 - HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive Image-Text-to-Text • 27B • Updated Apr 24 • 61.4k • 752 Shar514/Flux-Uncensored-V2 Image-to-Image • Updated May 11 • 25.3k • 48
HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive Image-Text-to-Text • 27B • Updated Apr 24 • 61.4k • 752
Qwen3.8-27B — MLX, multimodal preserved Qwen3.8-27B for Apple silicon — vision tower (333 tensors, bf16) and vendor MTP head both preserved and verified. 8-bit / 6-bit / 4-bit AWQ. Collection by avlp12 Aug 16 2 avlp12/Qwen3.8-27B-Alis-MLX-8bit Image-Text-to-Text • 27B • Updated Aug 22 • 373 • 9 avlp12/Qwen3.8-27B-Alis-MLX-6bit Image-Text-to-Text • 27B • Updated Aug 22 • 161 • 1 avlp12/Qwen3.8-27B-Alis-MLX-4bit Image-Text-to-Text • 27B • Updated Aug 22 • 233 • 4
🔥 Qwen 3.8 — Newest 27B, Korean-verified Qwen's newest 27B: vision, 262K context, Korean-verified. Start with IQ4_XS — we measured every tier and Q3_K_M is smaller yet slower. Needs 24GB+. Collection by batiai Aug 16 1 batiai/Qwen3.8-27B-GGUF Text Generation • 27B • Updated Aug 27 • 1.15k • 2 batiai/Qwen3.6-35B-A3B-GGUF Text Generation • 35B • Updated May 4 • 1.16k • 6 batiai/Qwen3.6-27B-GGUF Text Generation • 27B • Updated Aug 16 • 32.2k • 8