Inkling 2 Small is a general-purpose multimodal model that accepts text and image inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.
Alternatives to Inkling-2-Small
120 open-weight models that do the same job as Inkling-2-Small (383B vision), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
Authors: Meta Superintelligence Labs Model Release Date: October 2026 License: Muse Model License
822BA42B1M ctx muse-model-license14.4K 761Sept 2026- Same category
- Larger (822B vs 383B)
Step 3.7 Flash is a 198B-parameter sparse Mixture-of-Experts (MoE) vision-language model that combines a 196B-parameter language backbone with a 1.8B-parameter vision encoder for native image understanding.
201B256K ctx Apache 2.09.7K 463May 2026- Same category
- Similar size (201B vs 383B)
- Commercial use OK
We are delighted to introduce our MiniMax-VL-01 model. It adopts the "ViT-MLP-LLM" framework, which is a commonly used technique in the field of multimodal large language models.
456BA48.8B8K ctx Unknown licence5K 287Jan 2025- Same category
- Similar size (456B vs 383B)
Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.
1.03TA33.3B256K ctx modified-mit202.3K 1.6KApr 2026- Same category
- Larger (1.03T vs 383B)
- Commercial use OK
Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base.
1.03TA33.3B256K ctx modified-mit394.7K 2.9KJan 2026- Same category
- Larger (1.03T vs 383B)
- Commercial use OK
The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
424BA47B128K ctx Apache 2.0457 91Jun 2025- Same category
- Similar size (424B vs 383B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
125BA10B256K ctx Apache 2.0767.6K 658Feb 2026- Same category
- Smaller (125B vs 383B)
- Commercial use OK
The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
424BA47B128K ctx Apache 2.0268 26Jun 2025- Same category
- Similar size (424B vs 383B)
- Commercial use OK
Mistral Large 4 is our largest and most capable model to date: a 1 trillion-parameter natively multimodal Mixture-of-Experts model with 49 billion active parameters per token (52 billion including embeddings and output layers), trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in Mistral's…
1TA52B1M ctx Custom licence18.7K 1.7KSept 2026- Same category
- Larger (1T vs 383B)
The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
424BA47B128K ctx Apache 2.0243 68Jun 2025- Same category
- Similar size (424B vs 383B)
- Commercial use OK
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 is the full-precision release of NVIDIA Nemotron 3.5 Super VL, a vision-language model for reasoning, coding, tool use, document understanding, and video understanding.
124BA12B1M ctx openmdw-1.174.6K 131Oct 2026- Same category
- Smaller (124B vs 383B)
- Commercial use OK
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
402BA17B256K ctx Llama 4 Community License211 105Apr 2025- Same category
- Similar size (402B vs 383B)
Hy4 flash is our most cost-effective Hy model to date, featuring 220B total parameters (including 64B Engram parameters) with just 12B active parameters per token. It natively accepts text and image inputs, generates text, and supports a context window of up to 1M tokens.
220B1M ctx tencent-hy-license159 237Nov 2026- Same category
- Similar size (220B vs 383B)
- Newer release
Hy4 flash is our most cost-effective Hy model to date, featuring 220B total parameters (including 64B Engram parameters) with just 12B active parameters per token. It natively accepts text and image inputs, generates text, and supports a context window of up to 1M tokens.
219B1M ctx tencent-hy-license129 20Nov 2026- Same category
- Similar size (219B vs 383B)
- Newer release
💻 Run it on your own machine: POCKET-Darwin-180B-GGUF, the 4-bit GGUF of R3 (111 GB), runs on a laptop with an 8 GB GPU and 32 GB RAM, CPU only at 18–21 tok/s, a 128 GB mini PC or one DGX Spark. MMLU-Pro is identical to BF16 (87.65%).
180BA61.6B256K ctx qwen-community-1.0980 47Oct 2026- Same category
- Smaller (180B vs 383B)
💻 Run it on your own machine — POCKET-Darwin-180B-GGUF: the 4-bit GGUF of R3 (111 GB) runs on a laptop with an 8 GB GPU and 32 GB RAM, CPU only at 18–21 tok/s, a 128 GB mini PC or one DGX Spark — MMLU-Pro identical to BF16 (87.65%).
180BA61.6B256K ctx qwen-community-1.0787 139Sept 2026- Same category
- Smaller (180B vs 383B)
💻Github Repo • 🤗Model Collections • 📜Technical Report • 💬Online Chat
917BA22.9B256K ctx Apache 2.011K 277Feb 2026- Same category
- Larger (917B vs 383B)
- Commercial use OK
We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series.
241BA28B40K ctx Apache 2.0567 142Aug 2025- Same category
- Similar size (241B vs 383B)
- Commercial use OK
We are introducing Ling-3.0-flash-VL, our next-generation native multimodal model. Built upon Ling-3.0-flash, it brings visual information into the complete process of understanding, reasoning, acting, and verification—advancing beyond image and video perception to solving real-world tasks through…
125BA5.9B128K ctx MIT7.2K 128Sept 2026- Same category
- Smaller (125B vs 383B)
- Commercial use OK
Looking for a post-trained model? See the BF16 release for customization or the NVFP4 release for optimized deployment.
124BA12Bopenmdw-1.12.4K 63Oct 2026- Same category
- Smaller (124B vs 383B)
- Commercial use OK
The package downloads and caches the engine and weights on first use. This repository provides mirage.cact, mirage.safetensors and the model config.
?BApache 2.039.8K 446Nov 2026- Same category
- Commercial use OK
- Newer release
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
109BA18B10M ctx Llama 4 Community License109.7K 1.4KApr 2025- Same category
- Smaller (109B vs 383B)
This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.
108BA14.3B64K ctx MIT15.6K 726Aug 2025- Same category
- Smaller (108B vs 383B)
- Commercial use OK
This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.
108BA14.3B128K ctx MIT6K 398Dec 2025- Same category
- Smaller (108B vs 383B)
- Commercial use OK