Agentic coding LLM (24B) fine-tuned from Mistral-Small-3.1 with a 128K context window
12m
10K+
4
Qwen3 is the latest Qwen LLM, built for top-tier coding, math, reasoning, and language tasks.
11m
10K+
1
Advanced coding agent model with 80B params (3B active MoE) for code generation and debugging
7m
10K+
1
Newest LLama 3 release with improved reasoning and generation quality
1y
100K+
21
Granite-4.0-h-nano: lightweight instruct model trained via SFT, RL, and merging on diverse data.
11m
10K+
1
Kimi K2 Thinking: open-source agent with deep reasoning, stable tool use, fast INT4, 256k context.
10m
10K+
2
Qwen3 Embedding: multilingual models for advanced text/ranking tasks like retrieval & clustering.
10m
10K+
2
Embedding Gemma is a state-of-the-art text embedding model from Google DeepMind
11m
10K+
1
all-MiniLM-L6-v2 is a sentence-transformers, maps sentences & paragraphs to a 384 dimensional vector
11m
10K+
1
Multilingual reranking model for text retrieval, scoring document relevance across 119 languages.
10m
10K+
3
Multilingual reranking model for text retrieval, scoring document relevance across 119 languages.
10m
10K+
SmolLM3 is a 3.1B model for efficient on-device use, with strong performance in chat
1y
50K+
9
744B MoE language model with 40B active params for reasoning, coding, and agentic tasks (FP8)
7m
10K+
5
Kimi K2 Thinking: open-source agent with deep reasoning, stable tool use, fast INT4, 256k context.
10m
50K+
4
Image generation model, uses a base latent diffusion model plus a refiner.
8m
50K+
8
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks
11m
10K+
2
Ministral 3: compact vision-enabled model with near-24B performance, optimized for local edge use
10m
50K+
4
SmolVLM: lightweight multimodal model for video, image, and text analysis, optimized for devices.
11m
10K+
4
119B parameter hybrid model with reasoning, vision, and code capabilities (1M token context)
5m
10K+
1