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.
Compare Qwen3.8-4B-Distill with the top 3NVIDIA-Nemotron-3-Nano-4B-BF16 is a small language model (SLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response.
4B256K ctx nvidia-nemotron-open-model-license1.9M 143Mar 2026- Same category
- Similar size (4B vs 4.7B)
- Commercial use OK
- Widely used
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
- Similar size (4B vs 4.7B)
- Commercial use OK
- Widely used
Nanbeige4.2-3B is a compact agentic model built on Nanbeige4.2-3B-Base, designed to combine strong agentic behavior with broad reasoning and alignment capabilities. Its Looped Transformer architecture reuses the transformer layers to increase model capacity without adding parameters.
4.2B256K ctx Apache 2.089.1K 861Jul 2026- Same category
- Similar size (4.2B vs 4.7B)
- 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.
4B40K ctx Apache 2.03.1M 802Apr 2025- Same category
- Similar size (4B vs 4.7B)
- Commercial use OK
- Widely used
A little over a month has passed since Spark-X2.5. In the rapidly evolving world of AI agents, that is enough time to rethink, refine, and move the frontier forward.
4.1B1M ctx Apache 2.030.8K 1.1KOct 2026- Same category
- Similar size (4.1B vs 4.7B)
- Commercial use OK
- Newer release
Model Summary: Granite-4.1-3B is a 3B parameter long-context instruct model finetuned from Granite-4.1-3B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.
3.4B128K ctx Apache 2.0436K 118Apr 2026- Same category
- Similar size (3.4B vs 4.7B)
- 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 4.7B)
- Commercial use OK
- Newer release
NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 is a looped (latent-recurrent) large language model (LLM) trained by NVIDIA. The model employs a normalized-GPT architecture with interleaved hybrid sliding window attention (SWA) and full attention layers.
4B256K ctx openmdw-1.116.2K 261Oct 2026- Same category
- Similar size (4B vs 4.7B)
- Commercial use OK
- Newer release
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.
3.7B128K ctx Apache 2.040.8K 138Aug 2026- Same category
- Similar size (3.7B vs 4.7B)
- Commercial use OK
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.
2.5B128K ctx Apache 2.01M 1.9KSept 2026- Same category
- Similar size (2.5B 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.
3.8B256K ctx nvidia-nemotron-open-model-license81.1K 51Mar 2026- Same category
- Similar size (3.8B vs 4.7B)
- 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.
4B32K ctx Apache 2.0434.9K 118Apr 2025- Same category
- Similar size (4B vs 4.7B)
- Commercial use OK
UserRepGen-4B is a fine-tuned Qwen3.5-4B language model that generates a structured, natural-language user representation from a multi-turn user-assistant conversation.
4.5B256K ctx MIT2.5K 28Oct 2026- Same category
- Similar size (4.5B vs 4.7B)
- Commercial use OK
- Newer release
We are introducing Spark-X2.5-4B and Spark-X2.5-1.7B, two compact, general-purpose language models designed to make capable AI more practical, efficient, and accessible.
4.1B1M ctx Apache 2.08.3K 1.4KAug 2026- Same category
- Similar size (4.1B vs 4.7B)
- Commercial use OK
- Newer release
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 4.7B)
O Overall é a média aritmética simples dessas cinco métricas, com peso igual para cada uma. Nesse recorte, o Lumi-4B ocupa a 2ª posição entre 9 modelos.
4B256K ctx Unknown licence4.1K 75Oct 2026- Same category
- Similar size (4B vs 4.7B)
- Newer release
Agents‑A1 is a long-horizon agentic model from InternScience, built to scale heterogeneous agentic abilities across multiple domains including Long‑horizon Search, Engineering, Scientific Research, Instruction Following, and Tool-calling.
4.5B256K ctx Apache 2.02.3K 111Jul 2026- Same category
- Similar size (4.5B vs 4.7B)
- Commercial use OK
Jan-Code-4B is a code-tuned model built on top of Jan-v3-4B-base-instruct. It’s designed to be a practical coding model you can run locally and iterate on quickly—useful for everyday code tasks and as a lightweight “worker” model in agentic workflows.
4.4B256K ctx Apache 2.08K 83Mar 2026- Same category
- Similar size (4.4B vs 4.7B)
- Commercial use OK
Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.
9B256K ctx MIT822.7K 571Jun 2026- Same category
- Similar size (9B vs 4.7B)
- Commercial use OK
AREX is a family of deep research agents developed by the Beijing Academy of Artificial Intelligence (BAAI). It is designed for long-horizon tasks in which an agent must search across sources, assemble candidate answers, verify multiple constraints, and revise its research plan when the available…
4.5B256K ctx Apache 2.01.9K 53Jul 2026- Same category
- Similar size (4.5B vs 4.7B)
- Commercial use OK
NeoHorse-1-4B is a 4B causal language model and an initial prototype on the path toward recursive self-improvement (RSI). It is post-trained from Qwen3.5-4B for text-based agent harnesses, tool use, coding, and instruction following.
4.2B256K ctx Apache 2.02.8K 2.6KSept 2026- Same category
- Similar size (4.2B vs 4.7B)
- Commercial use OK
- Newer release
A little over a month has passed since Spark-X2.5. In the rapidly evolving world of AI agents, that is enough time to rethink, refine, and move the frontier forward.
4.1B1M ctx Apache 2.02.5K 48Oct 2026- Same category
- Similar size (4.1B vs 4.7B)
- Commercial use OK
- Newer release
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
8.2B40K ctx Apache 2.06.1M 2.2KApr 2025- Same category
- Similar size (8.2B vs 4.7B)
- Commercial use OK
- Widely used
NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8 is a looped (latent-recurrent) large language model (LLM) trained by NVIDIA. The model employs a normalized-GPT architecture with interleaved hybrid sliding window attention (SWA) and full attention layers.
4B256K ctx openmdw-1.12.6K 9Oct 2026- Same category
- Similar size (4B vs 4.7B)
- Commercial use OK
- Newer release