This checkpoint is a five-layer draft model for Qwen3.8-27B, with block size 16 and an 8,192-token sliding window.
Alternatives to Qwen3.8-27B-DSpine-b16
120 open-weight models that do the same job as Qwen3.8-27B-DSpine-b16 (2B 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.
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…
4.7B256K ctx Apache 2.0130.3K 74Aug 2026- Same category
- Larger (4.7B vs 2B)
- Commercial use OK
The 1.7B variant demonstrates significant advances over its predecessor SmolLM1-1.7B, particularly in instruction following, knowledge, reasoning, and mathematics.
1.7B8K ctx Apache 2.042.6K 168Oct 2024- Same category
- Similar size (1.7B vs 2B)
- 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.
2.6B125K ctx lfm1.06.7K 198Sept 2025- Same category
- Similar size (2.6B vs 2B)
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 License846.5K 3KSept 2024- Same category
- Similar size (3.2B vs 2B)
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-license70.4K 51Mar 2026- Same category
- Similar size (3.8B vs 2B)
- Commercial use OK
In August 2024, we released the first series of mathematical LLMs - Qwen2-Math - of our Qwen family. A month later, we have upgraded it and open-sourced Qwen2.5-Math series, including base models Qwen2.5-Math-1.5B/7B/72B, instruction-tuned models Qwen2.5-Math-1.5B/7B/72B-Instruct, and mathematical…
1.5B4K ctx Apache 2.0159.7K 67Sept 2024- Same category
- Similar size (1.5B vs 2B)
- 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.
752M40K ctx Apache 2.018.5M 1.9KApr 2025- Same category
- Smaller (752M vs 2B)
- 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 2.03.1K 15Jul 2026- Same category
- Similar size (3B vs 2B)
- Commercial use OK
ZR1-1.5B is a small reasoning model trained extensively on both verified coding and mathematics problems with reinforcement learning.
1.8B128K ctx MIT8.3K 78Apr 2025- Same category
- Similar size (1.8B vs 2B)
- Commercial use OK
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:
1.8B32K ctx Qwen Research License150.4K 86Jan 2024- Same category
- Similar size (1.8B vs 2B)
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-1.115.6K 259Oct 2026- Same category
- Similar size (4B vs 2B)
- Commercial use OK
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.
2.6B8K ctx Gemma Terms of Use170.2K 1.6KJul 2024- Same category
- Similar size (2.6B vs 2B)
K2-Horizon-0.9B is the compact dense member of the K2-Horizon family: a 0.9B-class decoder-only model with a 128K context window.
1.1B128K ctx Apache 2.011.7K 105Sept 2026- Same category
- Similar size (1.1B vs 2B)
- Commercial use OK
LFM2-2.6B-Exp is an experimental checkpoint built on LFM2-2.6B using pure reinforcement learning.
2.6B125K ctx lfm1.02.3K 345Dec 2025- Same category
- Similar size (2.6B vs 2B)
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 2B)
- Commercial use OK
In August 2024, we released the first series of mathematical LLMs - Qwen2-Math - of our Qwen family. A month later, we have upgraded it and open-sourced Qwen2.5-Math series, including base models Qwen2.5-Math-1.5B/7B/72B, instruction-tuned models Qwen2.5-Math-1.5B/7B/72B-Instruct, and mathematical…
1.5B4K ctx Apache 2.099.3K 124Sept 2024- Same category
- Similar size (1.5B vs 2B)
- Commercial use OK
Welcome to CoDA, Salesforce AI Research's diffusion-based language model designed for powerful code generation and bidirectional context understanding, presented in the paper CoDA: Coding LM via Diffusion Adaptation.
2B40K ctx CC BY-NC 4.0501 60Sept 2025- Same category
- Similar size (2B vs 2B)
Hunyuan is Tencent's open-source efficient large language model series, designed for versatile deployment across diverse computational environments.
1.8B256K ctx Unknown licence2.4K 604Jul 2025- Same category
- Similar size (1.8B vs 2B)
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 2B)
- Commercial use OK
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 MIT2.8K 865Jun 2026- Same category
- Similar size (3.1B vs 2B)
- Commercial use OK
Model Summary: Granite‑4.1‑3B‑Base is a decoder‑only language model with long‑context capabilities, designed to support a broad range of general text‑to‑text generation tasks, as well as fill‑in‑the‑Middle (FIM) code completion.
3.4B128K ctx Apache 2.010.9K 26Apr 2026- Same category
- Similar size (3.4B vs 2B)
- 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).
1.2B128K ctx Llama 3.2 Community License656.9K 2.8KSept 2024- Same category
- Similar size (1.2B vs 2B)
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 2.06.8K 52Jan 2026- Same category
- Similar size (3B vs 2B)
- Commercial use OK
Helium-1 is a lightweight language model with 2B parameters, targeting edge and mobile devices. It supports the 24 official languages of the European Union.
2B4K ctx CC BY-SA 4.01.2K 57Apr 2025- Same category
- Similar size (2B vs 2B)
- Commercial use OK