Qwen3.8-4B is a full-parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5-4B architecture. The student was trained on ~45,000 curated teacher traces from our internal Qwen3.8 distillation datasets — dense chain-of-thought spanning mathematics, general reasoning, and instruction following…
Alternatives to Qwen3.8-4B-Distill
120 open-weight models that do the same job as Qwen3.8-4B-Distill (4.7B 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.
We elaborate on the entire construction pipeline of AgentCPM-Explore on GitHub.
4B256K ctx Apache 2.02.3K 418Jan 2026- Same category
- Similar size (4B vs 4.7B)
- 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.
3.4B128K ctx Apache 2.023.8K 274Sept 2025- Same category
- Similar size (3.4B vs 4.7B)
- Commercial use OK
Model Summary: Granite-4.1-8B is a 8B parameter long-context instruct model finetuned from Granite-4.1-8B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.
8.8B128K ctx Apache 2.083.6K 258Apr 2026- Same category
- Similar size (8.8B vs 4.7B)
- 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 License4.2M 8.9KJul 2024- Same category
- Similar size (8B vs 4.7B)
- Widely used
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
8.2B32K ctx Apache 2.0600.1K 152Apr 2025- Same category
- Similar size (8.2B vs 4.7B)
- Commercial use OK
Apertus is a 70B and 8B parameter language model designed to push the boundaries of fully-open multilingual and transparent models.
8.1B64K ctx Apache 2.0218.5K 504Aug 2025- Same category
- Similar size (8.1B vs 4.7B)
- Commercial use OK
K2-Horizon-7B is the medium dense member of the K2-Horizon family: a 7B-core decoder-only model with a 512K context window.
9B512K ctx Apache 2.031K 288Sept 2026- Same category
- Similar size (9B vs 4.7B)
- Commercial use OK
- Newer release
Nemotron-Mini-4B-Instruct is a model for generating responses for roleplaying, retrieval augmented generation, and function calling. It is a small language model (SLM) optimized through distillation, pruning and quantization for speed and on-device deployment.
4B4K ctx NVIDIA Open Model License78.5K 192Sept 2024- Same category
- Similar size (4B vs 4.7B)
- 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 4.7B)
- Commercial use OK
- Newer release
AFM-4.5B-Base is a 4.5 billion parameter instruction-tuned model developed by Arcee.ai, designed for enterprise-grade performance across diverse deployment environments from cloud to edge.
4.6B64K ctx Apache 2.01.6K 36Jul 2025- Same category
- Similar size (4.6B vs 4.7B)
- Commercial use OK
SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports 6 languages, advanced reasoning and long context. SmolLM3 is a fully open model that offers strong performance at the 3B–4B scale.
3.1B64K ctx Apache 2.087.3K 180Jun 2025- Same category
- Similar size (3.1B vs 4.7B)
- Commercial use OK
The Phi-3-Mini-4K-Instruct is a 3.8B 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.
3.8B4K ctx MIT304.9K 1.5KApr 2024- Same category
- Similar size (3.8B vs 4.7B)
- Commercial use OK
Cohere Labs Tiny Aya is an open weights research release of a pretrained 3.35 billion parameter model optimized for efficient, strong, and balanced multilingual representation across 70+ languages, including many lower-resourced ones.
3.3BCC BY-NC 4.05.9K 33Feb 2026- Same category
- Similar size (3.3B vs 4.7B)
A compact 9B reasoning model distilled from DeepSeek-V4-Pro in Max Effect mode
9.4B256K ctx Apache 2.024.5K 7.4KOct 2026- Same category
- Larger (9.4B vs 4.7B)
- Commercial use OK
- Newer release
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.
8.5B256K ctx nvidia-nemotron-open-model-license49.7K 59Mar 2026- Same category
- Similar size (8.5B vs 4.7B)
- Commercial use OK
Apriel is a family of models built for versatility, offering high throughput and efficiency across a wide range of tasks.
4.8B16K ctx MIT3.9K 55Apr 2025- Same category
- Similar size (4.8B vs 4.7B)
- Commercial use OK
The Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets. This dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reasoning-dense properties.
3.8B128K ctx MIT240.2K 1.7KApr 2024- Same category
- Similar size (3.8B vs 4.7B)
- 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 2.027.4K 217Sept 2025- Same category
- Similar size (6.9B vs 4.7B)
- Commercial use OK
The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out).
3.2B128K ctx Llama 3.2 Community License317K 1.1KSept 2024- Same category
- Similar size (3.2B vs 4.7B)
We are releasing MiniCPM5-2B, the second model in the MiniCPM5 series, following MiniCPM5-1B. It is a dense 2B Transformer that scales up the same training recipe, built for on-device, local deployment, and resource-constrained scenarios, reaching 2B-class open-source SOTA.
2.5B512K ctx Apache 2.012.7K 34Aug 2026- Same category
- Similar size (2.5B vs 4.7B)
- Commercial use OK
- Newer release
Qwen3Guard is a series of safety moderation models built upon Qwen3 and trained on a dataset of 1.19 million prompts and responses labeled for safety.
8.2B32K ctx Apache 2.0110.5K 156Sept 2025- Same category
- Similar size (8.2B vs 4.7B)
- 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 lfm1.019.7K 808May 2026- Same category
- Similar size (8.5B vs 4.7B)
Bielik-4.5B-v3-Instruct is a generative text model featuring 4.6 billion parameters. It is an instruct fine-tuned version of the Bielik-4.5B-v3.
4.8BApache 2.02.4K 41Apr 2025- Same category
- Similar size (4.8B vs 4.7B)
- Commercial use OK
Model Summary: Granite-3.1-3B-A800M-Instruct is a 3B parameter long-context instruct model finetuned from Granite-3.1-3B-A800M-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets tailored for solving long context problems.
3.3BA800M128K ctx Apache 2.0114.9K 33Dec 2024- Same category
- Similar size (3.3B vs 4.7B)
- Commercial use OK