We introduce Spark-X2.6-1.7B, the second model in the Spark-X2.6 series, following the release of Spark-X2.6-4B. Building on Spark-X2.5-1.7B, this release further advances our compact, general-purpose language models for on-device deployment.
Alternatives to Spark-X2.6-1.7B
120 open-weight models that do the same job as Spark-X2.6-1.7B (1.7B 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.
A 1 B-parameter language model checkpoint built on the Hierarchical Reasoning Model (HRM) architecture, trained by Sapient Intelligence from scratch on structured public datasets.
1.2B4K ctx Apache 2.03.3K 838May 2026- Same category
- Similar size (1.2B vs 1.7B)
- Commercial use OK
We are releasing MiniCPM5-1B, the first model in the MiniCPM5 series. It is a dense 1B Transformer built for on-device, local deployment, and resource-constrained scenarios, reaching 1B-class open-source SOTA.
1.1B128K ctx Apache 2.06.9K 47May 2026- Same category
- Similar size (1.1B vs 1.7B)
- Commercial use OK
Youtu-LLM is a new, small, yet powerful LLM, contains only 1.96B parameters, supports 128k long context, and has native agentic talents.
2B128K ctx youtu-llm1.1K 43Dec 2025- Same category
- Similar size (2B vs 1.7B)
For more details about the training protocol of this model, please refer to the Falcon-H1 technical blogpost and Technical Report.
1.6B128K ctx Falcon LLM License4.7K 40May 2025- Same category
- Similar size (1.6B vs 1.7B)
SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports dual mode reasoning, 6 languages and long context. SmolLM3 is a fully open model that offers strong performance at the 3B–4B scale.
3.1B64K ctx Apache 2.0229.1K 1.1KJul 2025- Same category
- Similar size (3.1B vs 1.7B)
- Commercial use OK
This repository contains the weights for BitNet b1.58 2B4T, the first open-source, native 1-bit Large Language Model (LLM) at the 2-billion parameter scale, developed by Microsoft Research.
2B4K ctx MIT9.2K 1.5KApr 2025- Same category
- Similar size (2B vs 1.7B)
- Commercial use OK
Limite 1B - Violetto is Paradigma’s first model, designed for high-throughput solutions of difficult mathematical problems.
1B128K ctx Apache 2.03.7K 146Sept 2026- Same category
- Similar size (1B vs 1.7B)
- Commercial use OK
This is the model card for the first instruction tuned model of the EuroLLM series: EuroLLM-1.7B-Instruct. You can also check the pre-trained version: EuroLLM-1.7B.
1.7B4K ctx Apache 2.019.9K 104Aug 2024- Same category
- Similar size (1.7B vs 1.7B)
- Commercial use OK
ColGrep-Agent-2B is a lightweight code-localization agent designed to identify the files and line ranges relevant to a GitHub issue, bug report, feature request, or natural-language question about a repository.
2.5B128K ctx Apache 2.01.1K 39Oct 2026- Same category
- Similar size (2.5B vs 1.7B)
- 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 License2M 641Sept 2024- Same category
- Similar size (3.1B vs 1.7B)
- Widely used
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.
1.2B125K ctx Custom licence7.5K 153Jan 2026- Same category
- Similar size (1.2B vs 1.7B)
Falcon-H1 is a new series of large language models (LLMs) featuring hybrid architecture designs optimized for both high performance and efficiency across diverse use cases.
1.6B128K ctx Falcon LLM License3.8K 15May 2025- Same category
- Similar size (1.6B vs 1.7B)
🎉 License Updated! We are pleased to announce our more flexible licensing terms 🤗 ✈️ Try on FriendliAI (licensed under commercial purposes) 📢 EXAONE 4.0 is officially supported by HuggingFace transformers! Please check out the guide below
1.3B64K ctx exaone11.8K 195Jul 2025- Same category
- Similar size (1.3B vs 1.7B)
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
- Larger (3.7B vs 1.7B)
- Commercial use OK
LLM-jp-3.1 is a series of large language models developed by the Research and Development Center for Large Language Models at the National Institute of Informatics.
1.9B4K ctx Apache 2.02.5K 23May 2025- Same category
- Similar size (1.9B vs 1.7B)
- Commercial use OK
This is the model card for the first pre-trained model of the EuroLLM series: EuroLLM-1.7B. You can also check the instruction tuned version: EuroLLM-1.7B-Instruct.
1.7B4K ctx Apache 2.011.3K 123Aug 2024- Same category
- Similar size (1.7B vs 1.7B)
- Commercial use OK
We are releasing MiniCPM5-1B, the first model in the MiniCPM5 series. It is a dense 1B Transformer built for on-device, local deployment, and resource-constrained scenarios, reaching 1B-class open-source SOTA.
1.1B128K ctx Apache 2.04.3K 23May 2026- Same category
- Similar size (1.1B vs 1.7B)
- 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
- Larger (4B vs 1.7B)
- Commercial use OK
- Widely used
Model Summary: Granite-4.0-H-1B-Base is a lightweight decoder-only language model designed for scenarios where efficiency and speed are critical. They can run on resource-constrained devices such as smartphones or IoT hardware, enabling offline and privacy-preserving applications.
1.5B128K ctx Apache 2.01.4K 36Oct 2025- Same category
- Similar size (1.5B vs 1.7B)
- Commercial use OK
Large Action Models (LAMs) are advanced language models designed to enhance decision-making by translating user intentions into executable actions.
1.5B32K ctx CC BY-NC 4.03.9K 15Mar 2025- Same category
- Similar size (1.5B vs 1.7B)
Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters.
1.7B4K ctx Falcon LLM License4.1K 31Dec 2024- Same category
- Similar size (1.7B vs 1.7B)
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
1B32K ctx Gemma Terms of Use203.3K 1.3KMar 2025- Same category
- Similar size (1B vs 1.7B)
Model Summary: Granite-3.3-2B-Instruct is a 2-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities.
2.5B128K ctx Apache 2.040.8K 87Apr 2025- Same category
- Similar size (2.5B vs 1.7B)
- 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.
2.4B32K ctx exaone70.8K 198Dec 2024- Same category
- Similar size (2.4B vs 1.7B)