A compact 9B reasoning model distilled from DeepSeek-V4-Pro in Max Effect mode
Alternatives to DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
120 open-weight models that do the same job as DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic (9.4B 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.
Currently, most successful RL works, including open-source research, rely on relatively large base models, e.g., 32B models, particularly for enhancing code reasoning capabilities.
7.8B32K ctx MIT30.6K 281Apr 2025- Same category
- Similar size (7.8B vs 9.4B)
- Commercial use OK
📣 Update [10-07-2025]: Added a default system prompt to the chat template to guide the model towards more professional, accurate, and safe responses.
6.9BA1.5B128K ctx Apache 2.028.9K 217Sept 2025- Same category
- Similar size (6.9B vs 9.4B)
- Commercial use OK
T-lite-it-2.1 is an efficient Russian model built upon the Qwen 3 architecture, featuring significant improvements in instruction following and adds support for tool-calling capabilities — a key advancement over T-lite-it-1.0, which lacks tool-use support.
8.2B40K ctx Apache 2.03.1K 29Dec 2025- Same category
- Similar size (8.2B vs 9.4B)
- Commercial use OK
Bielik-11B-v3.1-Instruct is a generative text model featuring 11 billion parameters. It is an update to the Bielik 11B v3 line that expands multilingual continual pre-training and strengthens post-training for instruction following, tool use, and reasoning.
11.2B32K ctx Apache 2.0377 24Oct 2026- Same category
- Similar size (11.2B vs 9.4B)
- Commercial use OK
This repository contains AgentCPM-Report, an 8B-parameter deep research agent introduced in the paper AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research.
8.2B64K ctx Apache 2.02.2K 305Jan 2026- Same category
- Similar size (8.2B vs 9.4B)
- Commercial use OK
✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks!
8.2B64K ctx Apache 2.06.2K 391Sept 2025- Same category
- Similar size (8.2B vs 9.4B)
- Commercial use OK
ZGCM-1 is a 7.39B-parameter dense language model trained from scratch, built for mathematical reasoning and tool-assisted search. It combines deliberate internal thinking with active information gathering, supporting 256K-token context and both thinking and direct-response modes in a single model.
7.4B256K ctx MIT944 51Sept 2026- Same category
- Similar size (7.4B vs 9.4B)
- Commercial use OK
The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out).
8B128K ctx Llama 3.1 Community License135.6K 40Jul 2024- Same category
- Similar size (8B vs 9.4B)
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.
13.5B256K ctx nvidia-nemotron-open-model-license6.5K 157Apr 2026- Same category
- Similar size (13.5B vs 9.4B)
- Commercial use OK
NVIDIA-Nemotron-Nano-9B-v2-Base is a large language model (LLM) trained from scratch by NVIDIA that is designed as a completion model for a given piece of text. It uses a hybrid model architecture that consists primarily of Mamba-2 and MLP layers combined with just four Attention layers.
8.9BNVIDIA Open Model License2.7K 49Aug 2025- Same category
- Similar size (8.9B vs 9.4B)
- Commercial use OK
Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 7B Qwen2 model.
7.6B32K ctx Apache 2.0311.4K 698Jun 2024- Same category
- Similar size (7.6B vs 9.4B)
- Commercial use OK
Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens. Compared to the Qwen2.5 128K version, Qwen2.5-1M demonstrates significantly improved performance in handling long-context tasks while maintaining its capability in short tasks.
7.6B1M ctx Apache 2.052.4K 390Jan 2025- Same category
- Similar size (7.6B vs 9.4B)
- Commercial use OK
We expand on our Olmo model series by introducing Olmo Hybrid, a new 7B hybrid RNN model in the Olmo family. Olmo Hybrid dramatically outperforms Olmo 3 in final performance, consistently showing roughly 2x data efficiency on core evals over the course of our pretraining run.
7.4B32K ctx Apache 2.03.1K 17Feb 2026- Same category
- Similar size (7.4B vs 9.4B)
- Commercial use OK
Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the 7B Qwen2 base language model.
7.6B128K ctx Apache 2.0289.3K 181Jun 2024- Same category
- Similar size (7.6B vs 9.4B)
- Commercial use OK
We introduce PaCoRe (Parallel Coordinated Reasoning), a framework that shifts the driver of inference from sequential depth to coordinated parallel breadth, breaking the model context limitation and massively scaling test time compute: Think in Parallel: PaCoRe launches massive parallel exploration…
8.2B320K ctx MIT2.1K 49Dec 2025- Same category
- Similar size (8.2B vs 9.4B)
- Commercial use OK
Model Summary: Granite-3.1-8B-Instruct is a 8B parameter long-context instruct model finetuned from Granite-3.1-8B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets tailored for solving long context problems.
8.2B128K ctx Apache 2.033.6K 169Dec 2024- Same category
- Similar size (8.2B vs 9.4B)
- Commercial use OK
T5Gemma is a family of lightweight yet powerful encoder-decoder research models from Google. These models are created by adapting pretrained decoder-only models into a encoder-decoder.
5.6B8K ctx Gemma Terms of Use223.4K 10Jun 2025- Same category
- Similar size (5.6B vs 9.4B)
MiniCPM4 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.
8.2B32K ctx Apache 2.08.1K 289Jun 2025- Same category
- Similar size (8.2B vs 9.4B)
- Commercial use OK
MiniCPM4 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.
8.2B32K ctx Apache 2.08.1K 38Jun 2025- Same category
- Similar size (8.2B vs 9.4B)
- Commercial use OK
Currently, most successful RL works, including open-source research, rely on relatively large base models, e.g., 32B models, particularly for enhancing code reasoning capabilities.
7.8B32K ctx MIT15K 139Apr 2025- Same category
- Similar size (7.8B vs 9.4B)
- Commercial use OK
We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements:
4B256K ctx Apache 2.02.7M 1.1KAug 2025- Same category
- Smaller (4B vs 9.4B)
- Commercial use OK
- Widely used
This is the model card for EuroLLM-9B-Instruct. You can also check the pre-trained version: EuroLLM-9B.
9.2BApache 2.011.1K 229Nov 2024- Same category
- Similar size (9.2B vs 9.4B)
- Commercial use OK
K2-Horizon-3.7B is the small dense member of the K2-Horizon family: a 3.7B-core decoder-only model with a 512K context window.
5.1B512K ctx Apache 2.015.2K 116Sept 2026- Same category
- Similar size (5.1B vs 9.4B)
- Commercial use OK
The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.
7.2B32K ctx Apache 2.01.2M 3.3KDec 2023- Same category
- Similar size (7.2B vs 9.4B)
- Commercial use OK