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.
Granite Guardian 4.1 8B introduces improved Bring Your Own Criteria (BYOC) support, enabling users to define arbitrary judging criteria beyond the pre-baked safety and hallucination detectors.
8.4B128K ctx Apache 2.09.2K 52Apr 2026- Same category
- Similar size (8.4B vs 9.4B)
- Commercial use OK
NeoHorse-1-9B is a 9B causal language model and an initial prototype on the path toward recursive self-improvement (RSI). It is post-trained from Qwen3.5-9B for text-based agent harnesses, tool use, coding, and instruction following.
9B256K ctx Apache 2.01.4K 1.1KSept 2026- Same category
- Similar size (9B vs 9.4B)
- Commercial use OK
This is the model card for EuroLLM-9B-Instruct-2512, an improved version of utter-project/EuroLLM-9B-Instruct. In comparison with the previous version, this version includes the long-context extension phase and the revamped post-training recipe from utter-project/EuroLLM-22B-Instruct.
9.2B32K ctx Apache 2.06.4K 17Jan 2026- Same category
- Similar size (9.2B vs 9.4B)
- Commercial use OK
MiniCPM-SALA (Sparse Attention and Linear Attention) is the first large-scale hybrid model effectively integrating sparse and linear attention for million-token context modeling
9.5B512K ctx Apache 2.04K 685Feb 2026- Same category
- Similar size (9.5B vs 9.4B)
- Commercial use OK
We introduce Olmo 3, a new family of 7B and 32B models. This suite includes Base, Instruct, and Think variants. The Base models were trained using a staged training approach.
7.3B64K ctx Apache 2.0106.3K 93Sept 2025- Same category
- Similar size (7.3B vs 9.4B)
- Commercial use OK
The next iteration of Qwythos: all the reasoning of Qwythos-9B, with the looping behavior fixed. v2 keeps the deep chain-of-thought, the uncensored research posture, and the 1M-token context of its predecessor, and cleans up the rough edges that showed up in real use.
9.7B1M ctx Apache 2.01.3K 180Jul 2026- Same category
- Similar size (9.7B vs 9.4B)
- Commercial use OK
PLaMo-3-8B-Fin-Instruct is a Japanese language model for the financial domain, developed by Preferred Networks, Inc. It is fine-tuned from a PLaMo-3 base model through continued pre-training on financial corpora followed by supervised fine-tuning and direct preference optimization.
8.5B256K ctx plamo-community-license983 10Nov 2026- Same category
- Similar size (8.5B vs 9.4B)
- Newer release
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 9.4B)
ShieldGemma is a series of safety content moderation models built upon Gemma 2 that target four harm categories (sexually explicit, dangerous content, hate, and harassment).
9.2B8K ctx Gemma Terms of Use257.4K 31Jul 2024- Same category
- Similar size (9.2B vs 9.4B)
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 9.4B)
- 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 9.4B)
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 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.
8.5B4K ctx nvidia-nemotron-open-model-license8.4K 12Jan 2026- Same category
- Similar size (8.5B vs 9.4B)
- 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 9.4B)
- 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 9.4B)
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 9.4B)
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 9.4B)
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 9.4B)
- Commercial use OK
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 9.4B)
- Commercial use OK
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 9.4B)
- Commercial use OK
We introduce LLaDA, a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance.
8B4K ctx MIT105K 365Feb 2025- Same category
- Similar size (8B vs 9.4B)
- Commercial use OK
UserLM-2.0 is an 8-billion-parameter user simulator for user-AI conversations. Unlike typical language models trained to play the assistant, UserLM-2.0 generates the user side of a conversation. It is conditioned on a task intent that describes the user's high-level objective.
8B128K ctx MIT1.1K 15Oct 2026- Same category
- Similar size (8B vs 9.4B)
- Commercial use OK
LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.
8.3BA1B125K ctx lfm1.011.4K 376Oct 2025- Same category
- Similar size (8.3B vs 9.4B)
Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:
7.6B128K ctx Apache 2.0517K 343Sept 2024- Same category
- Similar size (7.6B vs 9.4B)
- Commercial use OK