Open-Weight & Local Models

Openly licensed models you can self-host or run locally, from Apache 2.0 to MIT and beyond.

78 models

Sarvam-105B

India

Sarvam AI's sovereign 105B-parameter Mixture-of-Experts model activating ~9B parameters per token, with a 128K-token context window. Trained on 12 trillion tokens across 22 Indian languages using 128 sparse experts with Multi-head Latent Attention and a custom low-fertility Indic tokenizer. Wins the majority of pairwise comparisons on Indian-language and STEM benchmarks.

Context
128K
Released
Jun 2026

Sarvam-1

India

Sarvam AI's compact 2B-parameter language model built from the ground up for Indian languages. Provides best-in-class performance across 10 Indic languages (bn, gu, hi, kn, ml, mr, or, pa, ta, te) alongside English, outperforming larger general-purpose models like Gemma-2-2B and Llama-3.2-3B thanks to careful data curation and an efficient Indic tokenizer. Edge-deployable.

Context
8K
Released
Jun 2026

Sarvam-30B

India

Sarvam AI's 30B-parameter Mixture-of-Experts reasoning model trained from scratch with only 2.4B active parameters per token. Optimized for real-time deployment and Indian languages, delivering strong reasoning, coding, and conversational performance while remaining efficient to serve. Open-weights.

Context
128K
Released
Jun 2026

GLM-5.2

China

Z.ai's (formerly Zhipu AI) flagship open-weight coding model with a 1M-token context window. Mixture-of-Experts architecture with 753B total parameters and ~40B active per request, featuring two cost-balancing reasoning modes. Tops several coding benchmarks while remaining a fraction of the cost of comparable proprietary frontier models. MIT-licensed weights.

Context
1.0M
Released
Jun 2026

Sarvam-M

India

Sarvam AI's 24B-parameter instruction-tuned model derived from Mistral-Small-3.1-24B, post-trained on English plus eleven major Indic languages (bn, hi, kn, gu, mr, ml, or, pa, ta, te). Delivers large relative gains on Indian-language, math, and programming benchmarks over its base model, with a hybrid reasoning mode for complex tasks.

Context
131K
Released
Jun 2026

Command A+

USA

Cohere's enterprise flagship model building on Command A with stronger reasoning, agentic tool use, and multilingual performance across 23 languages. Optimized for secure, high-throughput RAG, retrieval, and long-horizon agent workflows in regulated environments, with private and on-premise deployment options.

Context
256K
Released
Jun 2026

Kimi K2.7 Code

China

Moonshot AI's latest open-source, coding-focused model in the Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. A 1-trillion-parameter model that cuts reasoning token usage by roughly 30% versus K2.6 while improving coding and agent performance — +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite for multi-language support. Released under a Modified MIT License and available via Kimi APIs and Hugging Face.

Context
1.0M
Released
Jun 2026

DiffusionGemma

USA

Google DeepMind's experimental diffusion-based member of the Gemma 4 open model family. Unlike autoregressive models that generate text one token at a time, DiffusionGemma denoises a canvas of placeholder tokens to produce up to 256 tokens in parallel, finalizing output in one block. A Mixture-of-Experts model with 26B total parameters and 3.8B active per inference, delivering roughly 4x the throughput of similarly sized autoregressive Gemma models on local hardware. Excels at non-linear tasks like in-line editing, molecular sequencing, mathematical graphing, and self-correcting puzzles.

Context
262K
Released
Jun 2026

Nemotron 3 Ultra

USA

NVIDIA's flagship open 550B-parameter Mixture-of-Experts model with 55B active parameters, built for frontier reasoning and orchestration in long-running agentic systems. Features hybrid Mamba-Transformer architecture, LatentMoE routing, multi-token prediction, and NVFP4 precision for 5x higher throughput. Achieves 30% lower cost-to-task-completion on agentic benchmarks. Supports 1M+ token context window with 95% accuracy on Ruler@1M.

Context
1.0M
Released
Jun 2026

Gemma 4 12B

USA

Google's medium-size open-weight model with 12 billion parameters from the Gemma 4 family. Encoder-free unified multimodal architecture that natively processes text, image, audio, and video inputs without dedicated encoders. Features a 256K context window and supports 140+ languages. First medium-sized model capable of natively ingesting audio. Suitable for local deployment on GPUs with 16GB VRAM.

Context
262K
Released
Jun 2026

DBRX

USA

Databricks' open-source 132B parameter Mixture-of-Experts transformer model with 36B active parameters per input. Released under Databricks Open Model License, optimized for enterprise workloads including SQL generation and coding tasks.

Context
33K
Released
May 2026

Falcon 3 10B

UAE

TII's open-source 10B parameter model from the Falcon 3 family. Achieved number one position on Hugging Face's LLM leaderboard in its size category, outperforming Meta's Llama variants and other models under 13B parameters.

Context
33K
Released
May 2026

Snowflake Arctic

USA

Snowflake's enterprise-focused open LLM with 480B total parameters using a fine-grained MoE architecture with only 17B active parameters per input. Apache 2.0 licensed, excels at SQL generation, coding, and enterprise intelligence tasks with breakthrough training efficiency.

Context
4K
Released
May 2026

Jamba Large 1.7

Israel

AI21's latest hybrid SSM-Transformer model with Mixture-of-Experts architecture. Features a 256K context window, improved grounding and instruction-following. 94B total parameters with 398B active, optimized for enterprise long-context tasks.

Context
262K
Released
May 2026

Ring-2.6-1T

China

InclusionAI's (Ant Group) trillion-parameter open-weights reasoning model with 63B active parameters per token. Built for real-world agent workflows with adaptive reasoning-effort modes. Features hybrid linear and MLA attention architecture with MIT license.

Context
131K
Released
May 2026

Falcon-H1

UAE

TII's hybrid Mamba-Transformer model that outperforms comparable offerings from Meta's Llama and Alibaba's Qwen in the 30-70B parameter range. Designed for real-world AI on everyday devices and resource-limited settings with state-of-the-art efficiency.

Context
131K
Released
May 2026

StableLM 2 12B

UK

Stability AI's 12.1 billion parameter decoder-only language model pre-trained on 2 trillion tokens of diverse multilingual and code datasets. Supports multiple languages and offers strong performance for its compact size with instruction-tuned chat variant available.

Context
4K
Released
May 2026

Alloma 8B Instruct

Uzbekistan

Uzbek LLM Lab's 8B parameter instruction-tuned model optimized for the Uzbek language. Built on Llama architecture with a custom tokenizer averaging 1.7 tokens per Uzbek word versus 3.5 in original Llama, enabling 2x faster inference. Trained on 3.6B tokens with 4096 context length.

Context
4K
Released
May 2026

K2 Think

UAE

A 32 billion parameter open-weights reasoning model by LLM360/MBZUAI, built on Qwen2.5-32B. Trained with reinforcement learning and verifiable rewards for long chain-of-thought reasoning, agentic planning, and complex problem solving in math, science, and code.

Context
131K
Released
May 2026

MiniCPM-V 4.6

China

Ultra-efficient multimodal language model from OpenBMB built on SigLIP2-400M and Qwen3.5-0.8B (~1B parameters). Supports single-image, multi-image, and video understanding with mixed 4x/16x visual token compression. Designed for edge deployment on iOS, Android, and HarmonyOS.

Context
256K
Released
May 2026

Granite 4.1 8B

USA

IBM's dense decoder-only 8B parameter language model from the Granite 4.1 family. Supports 131K-token context, tool calling, RAG, code generation with fill-in-the-middle, text summarization, classification, and extraction across 12 languages. Released under Apache 2.0.

Context
131K
Released
May 2026

Granite 4.1 30B

USA

IBM's largest dense decoder-only 30B parameter language model from the Granite 4.1 family. Trained on approximately 15T tokens with long-context extension up to 512K tokens. Supports tool calling, RAG, code generation, multilingual tasks across 12 languages. Released under Apache 2.0.

Context
524K
Released
May 2026

DeepSeek V4 Pro

China

DeepSeek's flagship V4 model with 1.6T total parameters (49B activated). MoE architecture supporting 1M token context. Closes the gap with frontier proprietary models on reasoning and coding benchmarks.

Context
1.0M
Released
Apr 2026

DeepSeek V4 Flash

China

DeepSeek's efficient V4 model with 284B total parameters (13B activated). Optimized for speed and cost-efficiency while maintaining strong performance. Supports 1M token context window.

Context
1.0M
Released
Apr 2026

Hy3 Preview

China

Tencent's flagship open-weight Mixture-of-Experts model from the Hunyuan family with 295B total parameters and 21B active. Integrates fast and slow thinking modes with configurable reasoning effort. Designed for agentic workflows, cross-file code refactoring, long-document analysis, and multi-step tool use.

Context
256K
Released
Apr 2026

MiMo-V2.5-Pro

China

Xiaomi's flagship 1.02T-parameter Mixture-of-Experts model with 42B active parameters, built on a hybrid-attention architecture with 3-layer Multi-Token Prediction. Designed for complex agentic tasks, software engineering, and long-horizon instruction following with a 1M-token context window.

Context
1.0M
Released
Apr 2026

Qwen 3.6 27B

China

Alibaba's dense 27B parameter model that outperforms its own 397B MoE predecessor on agentic coding benchmarks. Strong multilingual and reasoning capabilities released under Apache 2.0.

Context
131K
Released
Apr 2026

Qwen 3.6 35B-A3B

China

Alibaba's efficient Mixture-of-Experts model with 35B total parameters and 3B active per token. Frontier-level agentic coding performance with 73.4% on SWE-bench Verified and 92.7 on AIME 2026. Released under Apache 2.0.

Context
131K
Released
Apr 2026

Gemma 4 26B

USA

Google's high-performance open-weight dense model with 26 billion parameters from the Gemma 4 family. Supports multimodal inputs including text and images with a 256K extended context window. Strong reasoning and code generation capabilities with all parameters active per forward pass.

Context
262K
Released
Apr 2026

Gemma 4 31B

USA

Google's flagship open-weight dense model with 31 billion parameters from the Gemma 4 family. All parameters active per forward pass with top-tier performance on reasoning benchmarks including AIME 2026 and MMLU Pro. Supports vision and extended 256K context window.

Context
262K
Released
Apr 2026

Gemma 4 E4B

USA

Google's efficient 4 billion parameter variant from the Gemma 4 family. Designed for resource-constrained environments while maintaining strong text generation quality. Text-only model with a 32K context window, balancing performance and efficiency.

Context
33K
Released
Apr 2026

Gemma 4 31B

USA

Google's flagship open-weight dense model with 31B parameters. All parameters active per forward pass. Ranks among top open models with strong performance on AIME 2026 (89.2%) and MMLU Pro (85.2%). Supports vision and extended context.

Context
262K
Released
Apr 2026

Gemma 4 E2B

USA

Google's efficient 2 billion parameter variant from the Gemma 4 family. Optimized for on-device and edge deployments with minimal resource requirements. Text-only model with a 32K context window, suitable for lightweight chat and completion tasks.

Context
33K
Released
Apr 2026

GPT-OSS 120B

USA

OpenAI's first open-weight large model with 120 billion parameters. Released under Apache 2.0 license, offering strong performance on reasoning and coding tasks while being fully self-hostable.

Context
131K
Released
Apr 2026

GPT-OSS 20B

USA

OpenAI's compact open-weight model with 20 billion parameters. Released under Apache 2.0 license, designed for efficient deployment on consumer hardware while maintaining strong coding and reasoning capabilities.

Context
131K
Released
Apr 2026

Nemotron 3 Super 120B

USA

NVIDIA's open hybrid Mamba-Transformer MoE model with 120B total parameters (12B active). Features 1M token context window and excels at agentic reasoning, coding, planning, and tool calling.

Context
1.0M
Released
Apr 2026

Qwen 3.6

China

Alibaba's latest Qwen model with enhanced reasoning, multilingual capabilities, and improved instruction following. Features strong performance on coding, math, and general knowledge benchmarks.

Context
131K
Released
Mar 2026

Mistral Small 4

France

Mistral AI's efficient hybrid model unifying instruct, reasoning, and coding in a single model. Open-weight under Apache 2.0 with strong performance for its size class.

Context
128K
Released
Mar 2026

Tiny Aya

USA

Compact multilingual language model from Cohere For AI with 3.35B parameters, optimized for efficient and balanced multilingual representation across 70+ languages including many lower-resourced ones. Designed for edge deployment without cloud dependency. Trained on 64 NVIDIA H100 GPUs with specialized regional variants available (Global, Earth, Fire).

Context
8K
Released
Feb 2026

DeepSeek V4

China

DeepSeek's fourth-generation model with improved mixture-of-experts architecture, enhanced reasoning and coding capabilities, and stronger multilingual performance. Competitive with frontier proprietary models.

Context
256K
Released
Feb 2026

Mistral Large 3

France

Mistral AI's largest open-weight model with 41B active parameters (675B total MoE). State-of-the-art general-purpose multimodal model with 256K context window and powerful agentic capabilities. Released under Apache 2.0.

Context
256K
Released
Dec 2025

GigaChat 3.1 Ultra

Russia

Sber's flagship large-scale Mixture-of-Experts model with 702B total parameters and 36B active. Designed for multilingual assistant workloads, reasoning, code generation, tool use, and large-cluster deployment. Open-weight release.

Context
32K
Released
Dec 2025

GigaChat 3.1 Lightning

Russia

Sber's compact Mixture-of-Experts model with 10B total parameters and 1.8B active. Designed for fast multilingual assistant workloads, reasoning, code, function calling, and product-style deployment on edge devices.

Context
8K
Released
Dec 2025

Devstral 2

France

Mistral AI's frontier code agents model designed for solving software engineering tasks. Open-weight model optimized for agentic coding workflows and complex development tasks.

Context
128K
Released
Dec 2025

GLM-4.7

China

Zhipu AI's multilingual agentic coding model with strong reasoning, tool use, and UI generation capabilities. Predecessor to GLM-5.1 with competitive performance on coding benchmarks.

Context
131K
Released
Oct 2025

AlemLLM

Kazakhstan

Kazakhstan's flagship Mixture-of-Experts language model developed by Astana Hub with technical support from 01.AI. Features 247B total parameters with 22B active per token, achieving state-of-the-art results on Kazakh, Russian, and English benchmarks. Outperforms GPT-4o on Kazakh language tasks.

Context
131K
Released
Aug 2025

Trendyol LLM 8B T1

Türkiye

Turkish-optimized 8B chat model developed by Trendyol, Turkey's largest e-commerce platform. Built on Qwen3-8B and fine-tuned on large-scale Turkish e-commerce datasets. Features advanced chain-of-thought reasoning in Turkish with dual operation modes (/think and /no_think), strong instruction following, summarization, coding, and attribute extraction for catalogue enrichment. English reasoning capabilities are preserved alongside Turkish.

Context
33K
Released
Jul 2025

YandexGPT 5 Lite

Russia

Yandex's compact 8B parameter language model trained on 15T tokens of primarily Russian and English text. Features 32K context window with strong performance on web, code, and mathematics tasks. Open-weight release.

Context
32K
Released
Jun 2025

Nemotron Nano 9B v2

USA

NVIDIA's compact 9B parameter model trained from scratch for both reasoning and non-reasoning tasks. Generates reasoning traces before final responses. Efficient for edge and on-device deployment.

Context
131K
Released
Jun 2025

WiroAI Turkish LLM 9B

Türkiye

Turkish-specialized 9B language model developed by WiroAI, built on Google's Gemma 2 architecture. Fine-tuned with Supervised Fine-Tuning (SFT) on over 500,000 carefully curated high-quality Turkish instructions, specifically adapted to Turkish culture and local context. Demonstrates superior performance on Turkish language processing tasks including conversation, reasoning, and instruction following.

Context
8K
Released
Apr 2025

Kumru 7B

Türkiye

Turkish large language model developed by VNGRS, pre-trained from scratch on 500 GB of Turkish corpora (300B tokens). Decoder-only architecture with a custom tokenizer optimized for Turkish, supporting code, math, and chat. Outperforms significantly larger multilingual models on the Cetvel Turkish benchmark. Available for on-premise enterprise deployment.

Context
8K
Released
Apr 2025

Llama 4 Scout

USA

Meta's efficient MoE model with 17B active parameters (109B total, 16 experts). Supports up to 10M token context — the longest of any production model. Strong performance on reasoning and multilingual tasks.

Context
10.0M
Released
Apr 2025

Llama 4 Maverick

USA

Meta's quality-focused MoE model with 17B active parameters (400B total, 128 experts). Targets quality-critical tasks with benchmark scores competitive with GPT-4o and Gemini 2.5 Pro.

Context
1.0M
Released
Apr 2025

Qwen3 32B

China

Alibaba's Qwen3 32B dense language model with strong reasoning and multilingual capabilities, supporting function calling and code generation across diverse tasks.

Context
131K
Released
Apr 2025

Qwen3 235B

China

Alibaba's Qwen3 235B mixture-of-experts model delivering frontier-level performance with advanced reasoning, function calling, and code generation capabilities at massive scale.

Context
131K
Released
Apr 2025

Qwen3 Coder

China

Alibaba's Qwen3 Coder model optimized for software development tasks including code generation, debugging, code review, and technical documentation with strong multilingual programming support.

Context
131K
Released
Apr 2025

Gemma 3 12B

USA

Google's mid-size open-weight model with 12 billion parameters from the Gemma 3 family. Supports multimodal inputs including text and images with a 128K context window. Strong performance on reasoning and code generation tasks at moderate compute cost.

Context
131K
Released
Mar 2025

Gemma 3 4B

USA

Google's compact open-weight model with 4 billion parameters from the Gemma 3 family. Supports multimodal inputs including text and images with a 128K context window. Balances efficiency and capability for vision and language tasks.

Context
131K
Released
Mar 2025

Gemma 3 1B

USA

Google's lightweight open-weight model with 1 billion parameters from the Gemma 3 family. Designed for on-device and resource-constrained deployments. Supports text-only tasks with a 32K context window. Efficient for chat and basic completion workloads.

Context
33K
Released
Mar 2025

Gemma 3 27B

USA

Google's largest open-weight model in the Gemma 3 family with 27 billion parameters. Supports multimodal inputs including text and images with a 128K context window. Delivers strong performance across reasoning, code generation, and vision tasks, competitive with larger proprietary models.

Context
131K
Released
Mar 2025

Mistral Small 3.1

France

Mistral AI's Small 3.1 model with 24B parameters offering efficient multimodal capabilities including vision, function calling, and code generation with a large 128K context window.

Context
128K
Released
Mar 2025

QwQ 32B

China

Alibaba's QwQ 32B reasoning-focused model designed for complex problem solving, mathematical reasoning, and step-by-step logical analysis with strong chain-of-thought capabilities.

Context
131K
Released
Mar 2025

Command A

USA

Cohere's flagship 111B parameter model optimized for demanding enterprises requiring fast, secure, and high-quality AI. Excels at RAG, tool use, and multilingual tasks with strong reasoning capabilities.

Context
256K
Released
Mar 2025

Phi-4 Mini

USA

Microsoft's Phi-4 Mini model with 3.8B parameters providing lightweight yet capable language understanding and code generation, optimized for resource-constrained deployments with a large 128K context window.

Context
128K
Released
Feb 2025

DeepSeek R1

China

DeepSeek's reasoning-focused model trained with reinforcement learning for complex multi-step reasoning. Excels at math, science, and coding problems requiring chain-of-thought reasoning.

Context
131K
Released
Jan 2025

Codestral

France

Mistral AI's cutting-edge code generation model specializing in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code completion, correction, and test generation. Features efficient architecture with 2x faster generation than its predecessor.

Context
256K
Released
Jan 2025

ISSAI KazLLM 1.0 70B

Kazakhstan

Large language model developed by ISSAI (Nazarbayev University) customized from Llama 3.1 70B to improve helpfulness of responses in the Kazakh language. Part of Kazakhstan's initiative to ensure the country benefits from generative AI advancements.

Context
128K
Released
Dec 2024

Llama 3.3 70B Instruct

USA

Meta's flagship open-weight model with 70 billion parameters. Strong multilingual capabilities with competitive performance on reasoning and coding benchmarks. Available for self-hosting and through various inference providers.

Context
131K
Released
Dec 2024

Phi-4

USA

Microsoft's Phi-4 model with 14B parameters excelling at reasoning and code generation tasks, delivering strong performance relative to its compact size with efficient inference characteristics.

Context
16K
Released
Dec 2024

DeepSeek V3

China

DeepSeek's third-generation large language model featuring mixture-of-experts architecture, strong multilingual capabilities, and competitive performance on reasoning and coding benchmarks.

Context
128K
Released
Dec 2024

Command R7B

USA

Cohere's compact 7B parameter model optimized for RAG, tool use, and code tasks. Delivers top-tier speed and efficiency on commodity GPUs and edge devices with 128K context window.

Context
128K
Released
Dec 2024

Cotype Nano

Russia

MTS AI's lightweight 1.5B parameter language model optimized for resource-constrained environments. Excels at Russian and English language tasks including content creation, translation, and text analysis. Runs efficiently on both CPU and GPU, including laptops and smartphones.

Context
32K
Released
Nov 2024

Aya Expanse 32B

USA

Highly performant 32B multilingual language model from Cohere For AI, designed to rival monolingual model performance across 23 languages. Built using innovations in multilingual data arbitrage, direct preference optimization, and model merging techniques. Outperforms previous multilingual models on both automatic and human evaluations.

Context
8K
Released
Oct 2024

Llama 3.2 90B Vision Instruct

USA

Meta's largest multimodal open-weight model with 90 billion parameters from the Llama 3.2 family. Delivers strong performance on both text and image understanding tasks with competitive results on visual reasoning benchmarks. Designed for high-quality inference requiring vision capabilities.

Context
131K
Released
Sep 2024

Llama 3.2 11B Vision Instruct

USA

Meta's multimodal open-weight model with 11 billion parameters from the Llama 3.2 family. Supports both text and image inputs, enabling visual understanding tasks alongside standard text generation. Suitable for applications requiring vision capabilities at moderate scale.

Context
131K
Released
Sep 2024

Llama 3.2 3B Instruct

USA

Meta's lightweight open-weight model with 3 billion parameters from the Llama 3.2 family. Designed for on-device and edge deployment with strong text generation capabilities relative to its size. Supports instruction following and general-purpose tasks.

Context
131K
Released
Sep 2024

Llama 3.1 8B Instruct

USA

Meta's efficient open-weight model with 8 billion parameters from the Llama 3.1 family. Optimized for instruction following with strong performance on general tasks, coding, and multilingual benchmarks. Ideal for cost-effective deployment and edge inference scenarios.

Context
131K
Released
Jul 2024

Whisper

USA

OpenAI's Whisper automatic speech recognition model capable of multilingual audio transcription and translation, trained on a large dataset of diverse audio for robust real-world performance.

Context
448
Released
Sep 2022