FermionResearch/Phonon-2
New automatic-speech-recognition model. Tags: mlx, parakeet_tdt_five_value, apple-silicon, speech-to-text, asr, stt, low-bit, quantization-aware-training
♥ 95
Models
New model releases and updates as they land.
161
ukisai/Swift-1.5-Qwen3.8-27b
New image-text-to-text model. Tags: qwen3_5, image-text-to-text, qwen3_8, reasoning, efficient-thinking, token-efficient, post-training, terminal-bench
♥ 89
interfaze-ai/lev
New zero-shot-classification model. Tags: peft, lev, system-one, decision-model, calibrated-decisions, classification, routing, moderation
♥ 98
Go Pro, go ad-free
Upgrade for an uninterrupted reading experience and priority access to new sources.
See pricingPSRben/VisionHOPE
New image-classification model. Tags: computer-vision, pytorch, visionhope, image-classification, arxiv:2609.33325, license:mit
♥ 133
NaiveAI/Naive-N0.5-Flash
New text-generation model. Tags: naive_n05_flash, moe, code, long-context, ai-research, text-generation, conversational, custom_code
♥ 98
ukisai/Swift-1.5-Qwen3.8-27B-GGUF
New image-text-to-text model. Tags: gguf, llama.cpp, qwen3_8, reasoning, efficient-thinking, token-efficient, post-training, terminal-bench
♥ 101
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF
New image-text-to-text model. Tags: gguf, gsq, rco, quantization, pruning, expert-pruning, mixed-precision, ist-daslab
♥ 97
akatz-ai/MiniMax-H3-Character-Swap-LoRA
New video-to-video model. Tags: diffusion-single-file, minimax-h3, lora, character-swap, video-editing, ref2va, comfyui, ai-toolkit
♥ 102
Alissonerdx/BFS-Best-Face-Swap
New image-to-image model. Tags: diffusers, lora, qwen-image, qwen-image-2.1, qwen-image-edit, face-swap, head-swap, body-swap
♥ 979
bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF
New image-text-to-text model. Tags: gguf, mimo_v2, agentic, distillation, supervised-fine-tuning, code, tool-use, image-text-to-text
♥ 100
orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF
New text-generation model. Tags: llama.cpp, gguf, qwen, qwen3.8, qwen3_5, orcasaq2, quantization, mixed-precision
♥ 107
black-forest-labs/flux-3-action-base
New robotics model. Tags: lerobot, robotics, flux, world-action-model, license:other
♥ 99
XingChen-AGI/TeleOCR
New image-text-to-text model. Tags: qwen2_5_vl, image-text-to-text, ocr, document-parsing, multimodal, conversational, custom_code, zh
♥ 605
SupersonicLabs/Julia-1
New text-classification model. Tags: pytorch, decision-model, text-classification, multilingual, routing, base_model:jhu-clsp/mmBERT-small, base_model:finetune:jhu-clsp/mmBERT-small, license:apache-2.0
♥ 104
PrunaAI/Pruna-Qwen-Image-2.1
New text-to-image model. Tags: diffusers, qwen, image-generation, image-editing, rgba, lora, distilled, few-step
♥ 101
KasugaiSakura/Qwen-Image-2.1-Uncensored-Abenzerps-GGUF
New text-to-image model. Tags: gguf, qwen, image-generation, comfyui, comfyui-gguf, text-to-image, base_model:Qwen/Qwen-Image-2.1, base_model:quantized:Qwen/Qwen-Image-2.1
♥ 116
fastino/GLiNER2.5-Decide
New token-classification model. Tags: gliner2, extractor, Text classification, Intent classification, Sentiment Analysis, Topic classification, Named Entity Recognition, token-classification
♥ 113
orcarouter/OrcaSAQ-2-27B
New text-generation model. Tags: vllm, qwen3_5, qwen, qwen3.8, orcasaq2, quantization, mixed-precision, 3-bit
♥ 112
Contrastive-LM/CLM-v0.1-8B
New text-ranking model. Tags: contrastive-lm, clm, contrastive-learning, verifier, reranker, agents, text-ranking, en
♥ 128
Edge0/Audio8-ASR-Infinite
New automatic-speech-recognition model. Tags: audio8_asr_infinite, text-generation, streaming, realtime, speech-recognition, audio, automatic-speech-recognition, custom_code
♥ 136