This is an official BlinkDL release of RWKV-7 Goose in Hugging Face Transformers format. RWKV-7 is an attention-free recurrent architecture with a constant-size recurrent state and constant inference work per generated token. Training remains parallelizable.
Alternatives to RWKV7-G1k-13.3B-20260930
120 open-weight models that do the same job as RWKV7-G1k-13.3B-20260930 (13.3B chat), 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.
Model Summary: Granite-3.3-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities.
8.2B128K ctx Apache 2.0100.7K 161Apr 2025- Same category
- Similar size (8.2B vs 13.3B)
- Commercial use OK
LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.
8.5BA1B125K ctx lfm1.03.1K 48May 2026- Same category
- Similar size (8.5B vs 13.3B)
Nemotron-Labs-Diffusion is a tri-mode language model that supports both AR decoding and diffusion-based parallel decoding by simply switching the attention pattern of the same model during inference.
8.5B4K ctx nvidia-nemotron-open-model-license8.4K 12Jan 2026- Same category
- Similar size (8.5B vs 13.3B)
- Commercial use OK
Large Action Models (LAMs) are advanced language models designed to enhance decision-making by translating user intentions into executable actions.
8B128K ctx CC BY-NC 4.0137.8K 66Mar 2025- Same category
- Similar size (8B vs 13.3B)
Granite is a family of open-source large language models developed by IBM, designed for enterprise and research use. Granite models are built to be versatile, safe, and efficient — covering a range of sizes and capabilities from compact edge-deployable models to large-scale reasoning systems.
29.3B128K ctx Apache 2.037.4K 143Aug 2026- Same category
- Larger (29.3B vs 13.3B)
- Commercial use OK
LLaDA2.0-mini-preview is a diffusion language model featuring a 16BA1B Mixture-of-Experts (MoE) architecture. As an enhanced, instruction-tuned iteration of the LLaDA series, it is optimized for practical applications.
16.3BA1.4B8K ctx Apache 2.01.7K 87Oct 2025- Same category
- Similar size (16.3B vs 13.3B)
- Commercial use OK
We introduce EXAONE 3.5, a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.
7.8B32K ctx exaone383.6K 160Dec 2024- Same category
- Similar size (7.8B vs 13.3B)
The Phi-3-Medium-4K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties.
14B4K ctx MIT23.7K 231May 2024- Same category
- Similar size (14B vs 13.3B)
- Commercial use OK
gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are safety reasoning models built-upon gpt-oss. With these models, you can classify text content based on safety policies that you provide and perform a suite of foundational safety tasks. These models are intended for safety use cases.
21.5BA4.8B128K ctx Apache 2.027.2K 293Sept 2025- Same category
- Similar size (21.5B vs 13.3B)
- Commercial use OK
MathForm-8B is an autoformalization model that translates natural-language mathematical statements into Lean 4. It is released with the paper MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement.
8.2B40K ctx Apache 2.02.2K 9Aug 2026- Same category
- Similar size (8.2B vs 13.3B)
- Commercial use OK
Tower+ 9B is build on top of Gemma 2 9B. The model goes through the Continuous Pretraining (CPT), Instruction Tuning (IT), Weighted Preference Optimization (WPO). During all stages we include parallel and multilingual data (covering 22 languages).
9.2B8K ctx CC BY-NC-SA 4.019K 42Jun 2025- Same category
- Similar size (9.2B vs 13.3B)
ALoDLM is a family of diffusion language models developed at Amazon, available as ALoDLM-1.7B and ALoDLM-8B and initialized from the corresponding Qwen3 backbones.
8.2B40K ctx CC BY-NC 4.01.5K 64Oct 2026- Same category
- Similar size (8.2B vs 13.3B)
- Newer release
gnani-evon-v3.3 is a hybrid Mamba architecture 30B MOE A3B model trained end-to-end for best-in-class Indic capability — continued pretraining, supervised fine-tuning, and reinforcement learning — delivering deep comprehension, extractive QA, and reasoning across Hindi, Bengali, Telugu, Tamil…
31.7BA3B128K ctx Apache 2.071.9K 84Aug 2026- Same category
- Larger (31.7B vs 13.3B)
- Commercial use OK
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
32.8B40K ctx Apache 2.03.4M 794Apr 2025- Same category
- Larger (32.8B vs 13.3B)
- Commercial use OK
- Widely used
M-Prometheus is a suite of open LLM judges that can natively evaluate multilingual outputs. They were trained on 480k instances of multilingual direct assessment and pairwise comparison data with long-form feedback. They can be prompted in the same way as Prometheus-2.
14.8B32K ctx Custom licence2.9K 13Apr 2025- Same category
- Similar size (14.8B vs 13.3B)
Velvet is an Italian family of large language models, developed from scratch, featuring a dense architecture. This model was trained on the HPC Leonardo infrastructure hosted by CINECA, utilizing public data that underwent extensive curation.
14.1BApache 2.02.8K 153Jan 2025- Same category
- Similar size (14.1B vs 13.3B)
- Commercial use OK
Last week, the release and buzz around DeepSeek-V2 have ignited widespread interest in MLA (Multi-head Latent Attention)! Many in the community suggested open-sourcing a smaller MoE model for in-depth research. And now DeepSeek-V2-Lite comes out:
15.7BA2.7B160K ctx DeepSeek License55.1K 173May 2024- Same category
- Similar size (15.7B vs 13.3B)
We introduce the updated version of the Qwen3-30B-A3B non-thinking mode, named Qwen3-30B-A3B-Instruct-2507, featuring the following key enhancements:
30.5BA3B256K ctx Apache 2.0802.5K 856Jul 2025- Same category
- Larger (30.5B vs 13.3B)
- Commercial use OK
ContextPilot-E4B is the Gemma4-E4B checkpoint of ContextPilot, a proactive context-management framework for long-horizon language-model agents. It teaches agents to plan, maintain long-term memory, and offload less useful context while they continue reasoning and using tools.
7.9B128K ctx Custom licence2.1K 9Aug 2026- Same category
- Similar size (7.9B vs 13.3B)
The GLM family welcomes new members, the GLM-4-32B-0414 series models, featuring 32 billion parameters. Its performance is comparable to OpenAI’s GPT series and DeepSeek’s V3/R1 series. It also supports very user-friendly local deployment features.
9.4B32K ctx MIT22.2K 111Apr 2025- Same category
- Similar size (9.4B vs 13.3B)
- Commercial use OK
Qwen1.5-MoE is a transformer-based MoE decoder-only language model pretrained on a large amount of data.
14.3BA2.7B8K ctx Qwen License40.9K 239Feb 2024- Same category
- Similar size (14.3B vs 13.3B)
Sentiment-Analysis-7B is a 7B-parameter autoregressive language model fine-tuned for sentiment classification of user messages directed at a service, product, or agent (the "Target").
7.2B32K ctx MIT3K 33Oct 2026- Same category
- Similar size (7.2B vs 13.3B)
- Commercial use OK
- Newer release
NVIDIA-Nemotron-Nano-9B-v2-Japanese is a large language model (LLM) trained from scratch by NVIDIA and designed as a unified model for both reasoning and non-reasoning tasks, specifically optimized for the Japanese language.
8.9B128K ctx nvidia-nemotron-open-model-license3.2K 146Feb 2026- Same category
- Similar size (8.9B vs 13.3B)
- Commercial use OK
We post-trained over Alibaba's Qwen3.8-27B to reinforce western values on a Chinese-trained model. We call this new model Arete-27B.
27.4B256K ctx Apache 2.07.5K 614Nov 2026- Same category
- Larger (27.4B vs 13.3B)
- Commercial use OK
- Newer release