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.
This is Huginn, version 01/25, a latent recurrent-depth model with 3.5B parameters, trained for 800B tokens on AMD MI250X machines. This is a proof-of-concept model, but surprisingly capable in reasoning and code given its training budget and size.
3.9BApache 2.020.7K 321Jan 2025- Same category
- Similar size (3.9B 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
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
2B40K ctx Apache 2.03M 622Apr 2025- Same category
- Smaller (2B vs 4.7B)
- Commercial use OK
- Widely used
Model Summary Granite-SWASH-3B-a600M is a 3B parameter decoder-only sparse language model with per-layer Sliding Window Attention (SWA) and learnable attention sinks (LSE-based).
3BA600M8K ctx Apache 2.03K 15Jul 2026- Same category
- Similar size (3B 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 lfm1.017K 808May 2026- Same category
- Similar size (8.5B vs 4.7B)
2.For harder math reasoning, try AMOBench , a problem set harder than the International Mathematical Olympiad (IMO), with included standard answers. Use it to evaluate VibeThinker against other SOTA models. Note: due to extreme difficulty, set max tokens to 60K–100K.
3.1B128K ctx MIT2.6K 865Jun 2026- Same category
- Similar size (3.1B vs 4.7B)
- 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.
7.4B64K ctx Apache 2.010.9K 66Jan 2026- Same category
- Similar size (7.4B 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 4.02.9K 72Feb 2026- Same category
- Similar size (3.3B vs 4.7B)
Trinity Nano Preview is a preview of Arcee AI's 6B MoE model with 1B active parameters. It is the small-sized model in our new Trinity family, a series of open-weight models for enterprise and tinkerers alike.
6.1BA1B128K ctx openmdw-1.12.6K 80Dec 2025- Same category
- Similar size (6.1B vs 4.7B)
- Commercial use OK
📝 Read the launch blog: Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint
8.8B128K ctx Apache 2.06.2K 56Oct 2026- Same category
- Similar size (8.8B vs 4.7B)
- Commercial use OK
- Newer release
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 4.7B)
This is the RL initialization checkpoint used in the blog JustRL II: Scaling Small LLMs to 128K Reasoning with a Critic (中文版).
2.8B64K ctx Unknown licence2.2K 8Sept 2026- Same category
- Similar size (2.8B vs 4.7B)
- Newer release
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 4.7B)
- Commercial use OK
BitCPM-CANN is the first end-to-end 1.58-bit (ternary) large language model training system natively built on Huawei Ascend NPU.
3B32K ctx Apache 2.03K 10May 2026- Same category
- Similar size (3B 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 2.06.6K 31Aug 2026- Same category
- Similar size (2.5B vs 4.7B)
- Commercial use OK
- Newer release
Jamba2 3B is an ultra-compact open source model designed to bring enterprise-grade reliability to on-device deployments. At just 3B parameters, it runs efficiently on consumer devices—iPhones, Androids, Macs, and PCs—while maintaining the grounding and instruction-following capabilities required…
3B256K ctx Apache 2.06.6K 53Jan 2026- Same category
- Similar size (3B vs 4.7B)
- Commercial use OK
Model Summary: Granite‑4.1‑8B‑Base is a decoder‑only language model with long‑context capabilities, designed to support a broad range of text‑to‑text generation tasks.
8.4B128K ctx Apache 2.014.4K 29Apr 2026- Same category
- Similar size (8.4B vs 4.7B)
- Commercial use OK
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:
3.1B32K ctx Qwen Research License218.8K 227Sept 2024- Same category
- Similar size (3.1B vs 4.7B)
Trinity Nano is an Arcee AI 6B MoE model with 1B active parameters. It is the small-sized model in our new Trinity family, a series of open-weight models for enterprise and tinkerers alike.
6.1BA1B128K ctx openmdw-1.11.9K 29Dec 2025- Same category
- Similar size (6.1B vs 4.7B)
- Commercial use OK
NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) 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.
8.9B128K ctx NVIDIA Open Model License130.2K 532Aug 2025- Same category
- Similar size (8.9B vs 4.7B)
- Commercial use OK
Hunyuan is Tencent's open-source efficient large language model series, designed for versatile deployment across diverse computational environments.
4.2B256K ctx Unknown licence987 30Jul 2025- Same category
- Similar size (4.2B 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.
2.5B128K ctx Apache 2.04.8K 23Sept 2026- Same category
- Similar size (2.5B vs 4.7B)
- Commercial use OK
- 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 4.7B)
LFM3-1.7B is a text model for local agents and specialized applications, based on our new tri-hybrid architecture.
1.7B256K ctx lfm1.0103.7K 1.8KOct 2026- Same category
- Smaller (1.7B vs 4.7B)
- Newer release