Model Library

Local AI model library

Browse open and open-weight models by task fit, memory requirement, quantization, runtime, and source confidence.

Models
62
Families
29
Artifacts
170
Human reviewed
1

DeepSeek-R1-Distill 70B

human-review-recommendedmit

DeepSeek-R1 distilled to Llama 70B base. Strong general reasoning.

DeepSeek70B66K contextQ4_K_M80GB reco
Task fit
ChatCodeRAG

DeepSeek-R1-Distill 32B

human-review-recommendedmit

DeepSeek-R1 reasoning model distilled to 32B. Excellent at math & logic.

DeepSeek32B66K contextQ4_K_M48GB reco
Task fit
ChatCodeRAG

Qwen3 235B-A22B

human-review-recommendedapache-2.0

Alibaba's flagship Qwen3. Competitive with GPT-4 class models.

Alibaba235B / 22B active131K contextQ2_K192GB reco
Task fit
ChatCodeRAGToolsAgent

Phi-4 14B

human-review-recommendedmit

Microsoft's compact 14B. Punches way above its weight, especially on math.

Microsoft14B16K contextQ4_K_M24GB reco
Task fit
ChatCodeRAG

GLM 5.1 FP8

Needs reviewmit

Z.ai's GLM 5.1 FP8. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Z.ai355B / 32B active131K contextFP896GB reco
Task fit
ChatRAGAgentTools

GLM 4.7 Flash

Needs reviewmit

Z.ai's GLM 4.7 Flash. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Z.ai32B131K contextQ4_K_M32GB reco
Task fit
ChatRAGAgentTools

Kimi K2.7 Code

Needs reviewother

Moonshot AI's Kimi K2.7 Code. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Moonshot AI1000B / 32B active262K contextQ4_K_M48GB reco
Task fit
VisionChatRAGCodeAgent

Kimi K2.6

Needs reviewother

Moonshot AI's Kimi K2.6. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Moonshot AI1000B / 32B active262K contextQ4_K_M48GB reco
Task fit
VisionChatRAGCodeAgent

Kimi K2 Thinking

Needs reviewother

Moonshot AI's Kimi K2 Thinking. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Moonshot AI1000B / 32B active262K contextQ4_K_M48GB reco
Task fit
ChatRAGCodeAgentTools

MiniMax M3

Needs reviewother

MiniMax's MiniMax M3. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

MiniMax456B / 46B active262K contextQ4_K_M64GB reco
Task fit
VisionChatRAGCodeAgent

MiniMax M3 MXFP8

Needs reviewother

MiniMax's MiniMax M3 MXFP8. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

MiniMax456B / 46B active262K contextMXFP8128GB reco
Task fit
VisionChatRAGCodeAgent

MiniMax M2.7

Needs reviewother

MiniMax's MiniMax M2.7. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

MiniMax230B / 10B active262K contextFP832GB reco
Task fit
ChatRAGCodeAgent

Gemma 4 31B It QAT W4a16 Ct

Needs reviewapache-2.0

Google's Gemma 4 31B It QAT W4a16 Ct. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Google31B131K contextQ4_032GB reco
Task fit
VisionChatRAG

Gemma 4 12B It QAT W4a16 Ct

Needs reviewapache-2.0

Google's Gemma 4 12B It QAT W4a16 Ct. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Google12B131K contextQ4_016GB reco
Task fit
VisionChatRAG

Gemma 4 E4B It QAT Q4 0 GGUF

Needs reviewapache-2.0

Google's Gemma 4 E4B It QAT Q4 0 GGUF. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Google4B131K contextQ4_012GB reco
Task fit
VisionChatRAG

FLUX.2 Dev

Needs reviewother

Black Forest Labs's FLUX.2 Dev. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Black Forest Labs32B128K contextFP16128GB reco
Task fit
Image

FLUX.2 Klein 9B

Needs reviewother

Black Forest Labs's FLUX.2 Klein 9B. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Black Forest Labs9B128K contextFP1648GB reco
Task fit
Image

FLUX.2 Klein 4B

Needs reviewapache-2.0

Black Forest Labs's FLUX.2 Klein 4B. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Black Forest Labs4B128K contextFP1640GB reco
Task fit
Image

Wan2.2 TI2V 5B

Needs reviewapache-2.0

Alibaba's Wan2.2 TI2V 5B. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Alibaba5B128K contextFP1640GB reco
Task fit
Video

Wan2.2 I2V A14B

Needs reviewapache-2.0

Alibaba's Wan2.2 I2V A14B. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Alibaba14B128K contextFP1664GB reco
Task fit
Video

LTX 2.3

Needs reviewother

Lightricks's LTX 2.3. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Lightricks13B128K contextFP1664GB reco
Task fit
VideoVision

LTX 2.3 FP8

Needs reviewother

Lightricks's LTX 2.3 FP8. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Lightricks13B128K contextFP840GB reco
Task fit
VideoVision

Wan2.2 T2V A14B

Needs reviewapache-2.0

Alibaba's Wan2.2 T2V A14B. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Alibaba14B128K contextFP1664GB reco
Task fit
Video

Qwen3.6 27B

Human reviewedapache-2.0

Alibaba's open-weight Qwen3.6 27B. Strong coding-agent, reasoning, long-context, and vision-language model with 262K native context.

Alibaba27B262K contextQ4_K_M32GB reco
Task fit
ChatCodeAgentRAGVision

Qwen3-Coder 30B-A3B

human-review-recommendedapache-2.0

Alibaba's Qwen3-Coder 30B with MoE architecture. Top coding model in <30B class.

Alibaba30.5B / 3.3B active262K contextQ4_K_M48GB reco
Task fit
CodeAgentTools

Qwen2.5-Coder 32B

human-review-recommendedapache-2.0

Qwen 2.5 Coder 32B. Predecessor to Qwen3-Coder, still very capable.

Alibaba32B33K contextQ4_K_M48GB reco
Task fit
CodeAgentTools

GLM 5.2 FP8

Needs reviewmit

Z.ai's GLM 5.2 FP8. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Z.ai355B / 32B active131K contextFP896GB reco
Task fit
ChatRAGAgentTools

Kimi K2.5

Needs reviewother

Moonshot AI's Kimi K2.5. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Moonshot AI1000B / 32B active262K contextQ4_K_M48GB reco
Task fit
VisionChatRAGCodeAgent

Kimi K2 Instruct 0905

Needs reviewother

Moonshot AI's Kimi K2 Instruct 0905. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Moonshot AI1000B / 32B active262K contextFP896GB reco
Task fit
ChatRAGCodeAgentTools

MiniMax M2.5

Needs reviewother

MiniMax's MiniMax M2.5. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

MiniMax230B / 10B active262K contextFP832GB reco
Task fit
ChatRAGCodeAgent

DeepSeek-Coder-V2 Lite 16B

human-review-recommendeddeepseek

DeepSeek's efficient MoE coder. 16B total / 2.4B active.

DeepSeek16B / 2.4B active128K contextQ4_K_M24GB reco
Task fit
CodeAgentTools

Llama 3.3 70B

human-review-recommendedllama

Meta's Llama 3.3 70B. Strong all-rounder, 128K context.

70B131K contextQ4_K_M80GB reco
Task fit
ChatCodeRAGTools

MiniMax M2

Needs reviewother

MiniMax's MiniMax M2. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

MiniMax230B / 10B active262K contextFP832GB reco
Task fit
ChatRAGCodeAgent

Diffusiongemma 26B A4B It

Needs reviewapache-2.0

Google's Diffusiongemma 26B A4B It. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Google26B / 4B active128K contextFP16128GB reco
Task fit
ImageVision

Devstral 24B

human-review-recommendedapache-2.0

Mistral's coding-focused model. Strong agent capabilities.

Mistral AI24B128K contextQ4_K_M32GB reco
Task fit
CodeAgent

Kimi VL A3B Thinking 2506

Needs reviewmit

Moonshot AI's Kimi VL A3B Thinking 2506. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Moonshot AI3B262K contextQ4_K_M8GB reco
Task fit
VisionChatRAGCodeAgent

FLUX.1 Kontext Dev

Needs reviewother

Black Forest Labs's FLUX.1 Kontext Dev. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Black Forest Labs8B128K contextFP1648GB reco
Task fit
Image

Stable Diffusion 3.5 Medium

Needs reviewother

Stability AI's Stable Diffusion 3.5 Medium. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Stability AI2.5B128K contextFP1624GB reco
Task fit
Image

Qwen3 30B-A3B

human-review-recommendedapache-2.0

Qwen3 30B with MoE. Same family as Coder, general-purpose.

Alibaba30.5B / 3.3B active131K contextQ4_K_M48GB reco
Task fit
ChatCodeRAGTools

Stable Diffusion 3.5 Large

Needs reviewother

Stability AI's Stable Diffusion 3.5 Large. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Stability AI8B128K contextFP1648GB reco
Task fit
Image

Wan2.2 S2V 14B

Needs reviewapache-2.0

Alibaba's Wan2.2 S2V 14B. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Alibaba14B128K contextFP1664GB reco
Task fit
Video

Wan2.2 Animate 14B

Needs reviewapache-2.0

Alibaba's Wan2.2 Animate 14B. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Alibaba14B128K contextFP1664GB reco
Task fit
Video

LTX 2.3 Nvfp4

Needs reviewother

Lightricks's LTX 2.3 Nvfp4. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Lightricks13B128K contextNVFP424GB reco
Task fit
VideoVision

Mistral Small 3.1 24B

human-review-recommendedapache-2.0

Mistral Small 3.1 with vision. Strong multilingual support.

Mistral AI24B128K contextQ4_K_M40GB reco
Task fit
ChatVisionToolsCode

Gemma 4 E2B It QAT Mobile Transformers

Needs reviewapache-2.0

Google's Gemma 4 E2B It QAT Mobile Transformers. Auto-imported from Hugging Face seed; review memory and benchmark details before using for final ranking.

Google2B131K contextQ4_K_M8GB reco
Task fit
VisionChatRAG

Gemma 3 27B

human-review-recommendedgemma

Google's open multimodal 27B. Vision + language in one model.

Google27B128K contextQ4_K_M40GB reco
Task fit
ChatVisionCode

Qwen3 8B

human-review-recommendedapache-2.0

Qwen3 8B. Compact general-purpose, runs on any laptop.

Alibaba8.2B131K contextQ4_K_M16GB reco
Task fit
ChatCodeRAGTools

Qwen2.5-VL 32B

human-review-recommendedapache-2.0

Qwen 2.5 VL (Vision-Language). Top open vision model.

Alibaba32B33K contextQ4_K_M48GB reco
Task fit
VisionChatCode

LLaVA-1.6 34B

human-review-recommendedapache-2.0

LLaVA 1.6 multimodal model. Image understanding + chat.

34B4K contextQ4_K_M48GB reco
Task fit
VisionChat

Wan2.1 14B

human-review-recommendedapache-2.0

Alibaba's Wan 2.1 text-to-video. Open weights, runs on consumer GPUs.

14BContext unknownFP1648GB reco
Task fit
Video

CogVideoX 5B

human-review-recommendedapache-2.0

Zhipu AI's CogVideoX 5B. Compact open video model.

5BContext unknownFP1624GB reco
Task fit
Video

BGE-M3 Embedding

human-review-recommendedmit

BAAI's BGE-M3. Multilingual embedding for RAG.

0.6B8K contextFP168GB reco
Task fit
RAG

Nomic Embed Text v1.5

human-review-recommendedapache-2.0

Nomic AI's text embedding. Long context, fully open.

0.3B8K contextFP164GB reco
Task fit
RAG

Whisper Large v3

human-review-recommendedmit

OpenAI's Whisper Large v3. Top open ASR model.

OpenAI1.5BContext unknownFP168GB reco
Task fit
Voice

F5-TTS

human-review-recommendedmit

F5-TTS. Open-source TTS with voice cloning.

0.3BContext unknownFP168GB reco
Task fit
Voice

CosyVoice 300M

human-review-recommendedapache-2.0

Alibaba's CosyVoice. Multilingual TTS with emotion control.

0.3BContext unknownFP168GB reco
Task fit
Voice

SmolLM2 1.7B

human-review-recommendedapache-2.0

Hugging Face's SmolLM2 1.7B. Tiny but capable, fits anywhere.

1.7B8K contextQ4_K_M4GB reco
Task fit
ChatRAG

FLUX.1-dev

human-review-recommendedapache-2.0

Black Forest Labs' state-of-the-art text-to-image model. Top of GenEval.

Black Forest Labs12BContext unknownFP1648GB reco
Task fit
Image

Stable Diffusion XL

human-review-recommendedopenrail

Stability AI's classic SDXL. Best bang/buck for image gen.

3.5BContext unknownFP1616GB reco
Task fit
Image

HunyuanVideo 13B

human-review-recommendedtencent

Tencent's open HunyuanVideo. 13B params, high quality.

13BContext unknownFP1648GB reco
Task fit
Video

Llama 3.2 3B

human-review-recommendedllama

Meta's tiny Llama 3.2 3B. Runs on phones & weak hardware.

3.2B131K contextQ4_K_M8GB reco
Task fit
ChatRAG

Gemma 3n 4B

human-review-recommendedgemma

Google's Gemma 3n. Multimodal (text/vision/audio) at 4B size.

4B33K contextQ4_K_M8GB reco
Task fit
ChatVisionVoice