All Hugging Face Models
Zephyr 7B (HuggingFace)
A fine-tuned version of Mistral-7B that performs well on chat benchmarks.
Qwen3 30B A3B
Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen3.5-397B-A17B
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3-235B-A22B-Thinking-2507
Qwen reasoning model for deliberate problem solving, math, and coding
Qwen3.6 35B-A3B
Open multimodal Qwen MoE for local agents that need vision, audio, and code
Qwen 3 Embedding 8B
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Qwen3.8 2.4T A95B
Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen3-Next-80B-A3B-Instruct
Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen 3 Embedding 4B
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
GLM-4.5V
GLM vision model for visual reasoning, documents, and multimodal agents
GLM-4.5-Air
Lighter GLM-4.5 variant for fast coding assistance and cheaper agents
GLM-5.1
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
GLM-4.5
Hybrid-reasoning GLM release that made the 4.5 line broadly useful
GLM-4.6
Late GLM-4 workhorse for coding agents, reasoning, and structured tasks
GLM-5
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
GLM-4.7
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
GLM-4.7-Flash
Efficient GLM model for fast reasoning, coding, and agent workflows
Inkling Small
Efficient model for low-latency assistance, extraction, and routine automation
Llama-3.1-8B-Instruct
Open Llama instruction model for multilingual chat, reasoning, and coding
MiMo-V2-Flash
MiMo flash model for fast multimodal assistance and agent workflows
MiMo-V2.5
MiMo model for long-context reasoning, perception, and agentic tasks
MiniMax-M2.7
MiniMax model for chat, coding, office work, and agentic tasks
MiniMax-M2.1
MiniMax model for chat, coding, office work, and agentic tasks
MiniMax-M2
Efficient open MiniMax model built for coding agents and tool-heavy workflows
MiniMax-M3
MiniMax multimodal model for long-context coding, perception, and agent planning
MiniMax-M2.5
MiniMax model for chat, coding, office work, and agentic tasks
Gemma 4 26B A4B IT
Open Gemma instruction model for efficient chat and self-hosted deployments
Kimi-K2.5
Kimi multimodal agent model for visual understanding, coding, and planning
Kimi K2.7 Code
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking
Kimi-K2-Instruct-0905
Kimi model for long-context chat, coding, and agentic reasoning
Kimi-K2-Thinking
Kimi reasoning model for long-horizon research, planning, and tool use
Kimi K3
Kimi multimodal agent model for visual understanding, coding, and planning
Kimi-K2.6
Kimi multimodal agent model for visual understanding, coding, and planning
Kimi-K2-Instruct
Kimi model for long-context chat, coding, and agentic reasoning
GPT OSS 20B
Open-weight GPT model for self-hosted reasoning and instruction-following workloads
DeepSeek V4 Pro
Open MoE flagship with million-token context for coding and long agent runs
DeepSeek V4 Flash 0731
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
DeepSeek-V3.2
DeepSeek chat model for instruction following, coding, and analysis
DeepSeek-R1-0528
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
DeepSeek-V3.1
DeepSeek chat model for instruction following, coding, and analysis
DeepSeek V3 0324
DeepSeek chat model for instruction following, coding, and analysis
DeepSeek V4 Pro 0813
Flagship DeepSeek model for coding, reasoning, and agentic work
DeepSeek-V3
DeepSeek chat model for instruction following, coding, and analysis
DeepSeek V4 Flash
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
Step 3.5 Flash
StepFun flash lane for quick multimodal reasoning and coding assistance
Qwen3 235B-A22B Instruct 2507
Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen3 VL 235B A22B Thinking
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3 VL 235B A22B Instruct
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3.6 27B
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3.5 9B
Qwen instruction model for multilingual chat, reasoning, and tool use
Qwen3.5 122B-A10B
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3 32B
Dense open Qwen model for self-hosted chat, reasoning, and coding
Qwen3 235B-A22B
Large open Qwen MoE for multilingual reasoning, coding, and tool use
Qwen3-Coder-Next
Qwen coding model for software agents, repository edits, and code reasoning
Qwen3-Coder 30B-A3B Instruct
Smaller Qwen coder for efficient local agents and repo-level fixes
Qwen3.5 27B
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen3.5 35B-A3B
Qwen vision-language model for visual reasoning, documents, and agent tasks
Qwen2.5-Coder-32B-Instruct
Qwen coding model for software agents, repository edits, and code reasoning
Qwen3-Next-80B-A3B-Thinking
Qwen reasoning model for deliberate problem solving, math, and coding
Llama 3.3 70B (HF)
Popular open Llama workhorse for multilingual chat, coding, and self-hosting.
Gemma 4 31B IT (HF)
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning.
DeepSeek-R1 (HF)
Classic open reasoning model for transparent math, coding, and deliberate problem solving.
GPT OSS 120B (HF)
Open GPT reasoning model for self-hosted agents and controllable deployments.
Qwen3 Coder 480B A35B (HF)
Qwen coding model for software agents, repository edits, and code reasoning.
Step 3.7 Flash (HF)
Newer StepFun flash model for faster agents, coding, and multimodal prompts.
MiMo-V2.5-Pro (HF)
Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution.
Hy3 (HF)
Tencent Hy reasoning model for coding, instruction following, and agent tasks.
Inkling (HF)
Multimodal model for analyzing text, images, documents, and rich media.
GLM 5.2 (HF)
Open flagship GLM for long-horizon coding agents and million-token context work.
