전체 검색
AI 모델 84762
- unity-csharp-coder↗
HussainIsWashed
- granite-4.2-30b↗
ibm-granite
Granite is a family of open-source large language models developed by IBM, designed for enterprise and research use. Granite models are built to be versatile, safe, and efficient — covering a range of sizes and capabilities from compact edge-deployable models to large-scale reasoning systems. All Granite models are released under the Apache 2.0 license, enabling unrestricted commercial and academic use. The Granite 4.2 generation introduces native reasoning (thinking) capabilities, allowing models to perform step-by-step chain-of-thought reasoning before producing final answers. This significantly improves performance on complex math, coding, multi-step logic, and agentic tool-calling tasks. **Granite-4.2-30B** is the flagship reasoning model in the Granite 4.2 family. It delivers the strongest performance across reasoning-intensive tasks by leveraging built-in ` ... ` chain-of-thought. It supports flexible thinking modes — full thinking (default), non-thinking, and low-effort — allowing users to balance depth vs. latency on a per-query basis.
- Jais-ASR↗
IFM
- LoopedLM-P2-huginn-s-orthoinj↗
IFM
- cortex-0.3-0.02b-mlx↗
Ilides
- DeepSeek-R1-Distill-Llama-70B-Uncensored-v2-Unbiased-Reasoner-i1-GGUF↗
IMUGLYHUH
- gemma-4-31B-it-int4-AutoRound↗
Intel
This model is an int4 model with group_size 128 and symmetric quantization of google/gemma-4-31B-it generated by intel/auto-round. Please follow the license of the original model. A youtube video by Fahd Mirza demonstrates how to use this model. MODEL_ID = "Intel/gemma-4-31B-it-int4-AutoRound" processor = AutoProcessor.from_pretrained(MODEL_ID) model = AutoModelForCausalLM.from_pretrained( MODEL_ID, dtype="auto", device_map="auto" )
- Muse-Spark-Open-816B-A42B-GGUF↗
Interchained
- AuroLA-7B-PT↗
Jazzcharles
- jina-embeddings-v5-omni-nano-classification-mlx↗
jinaai
