selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

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.

the original
tencent logo≈1.9 GB

This checkpoint is a five-layer draft model for Qwen3.8-27B, with block size 16 and an 8,192-token sliding window.

2B256K ctx Apache 2.0
4.9KNov 2026gguf
--vram
any
--gpus
--quant
  1. lightonai logo

    colgrep-agent-2B

    lightonai·Chat

    ≈2.3 GB

    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 2.0
    1.1KOct 2026gguf
    • Same category
    • Similar size (2.5B vs 2B)
    • Commercial use OK
    vs
  2. Qwen logo≈2.6 GB

    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 License
    2.1MSept 2024ollama
    • Same category
    • Similar size (3.1B vs 2B)
    • Widely used
    vs
  3. microsoft logo

    bitnet-b1.58-2B-4T

    microsoft·Chat

    ≈2.0 GB

    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 MIT
    9.6KApr 2025gguf
    • Same category
    • Similar size (2B vs 2B)
    • Commercial use OK
    vs
  4. Qwen logo

    Qwen2.5-1.5B

    Qwen·Chat

    ≈1.6 GB

    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:

    1.5B128K ctx Apache 2.0
    504.7KSept 2024gguf
    • Same category
    • Similar size (1.5B vs 2B)
    • Commercial use OK
    vs
  5. ibm-granite logo

    granite-4.2-3b

    ibm-granite·Chat

    ≈3.3 GB

    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 2.0
    42.3KAug 2026ollama
    • Same category
    • Similar size (3.7B vs 2B)
    • Commercial use OK
    vs
  6. allenai logo

    OLMo-2-0425-1B

    allenai·Chat

    ≈1.9 GB

    We introduce OLMo 2 1B, the smallest model in the OLMo 2 family. OLMo 2 was pre-trained on OLMo-mix-1124 and uses Dolmino-mix-1124 for mid-training.

    1.5B4K ctx Apache 2.0
    114.1KApr 2025gguf
    • Same category
    • Similar size (1.5B vs 2B)
    • Commercial use OK
    vs
  7. Qwen logo

    Qwen3-4B

    Qwen·Chat

    ≈4.0 GB

    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 2.0
    3.2MApr 2025ollama
    • Same category
    • Similar size (4B vs 2B)
    • Commercial use OK
    • Widely used
    vs
  8. tencent logo

    Youtu-LLM-2B-Base

    tencent·Chat

    ≈4.7 GB

    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-llm
    1.2KDec 2025gguf
    • Same category
    • Similar size (2B vs 2B)
    vs
  9. Vxtzq logo

    Crowd-v1

    Vxtzq·Chat

    ≈1.4 GB

    Crowd-v1 is the first official model architecture released for CrowdGPT, a community-driven distributed AI project.

    1BMIT
    91KAug 2026
    • Same category
    • Smaller (1B vs 2B)
    • Commercial use OK
    vs
  10. LGAI-EXAONE logo

    EXAONE-3.5-2.4B-Instruct

    LGAI-EXAONE·Chat

    ≈2.5 GB

    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 exaone
    72.7KDec 2024ollama
    • Same category
    • Similar size (2.4B vs 2B)
    vs
  11. LiquidAI logo

    LFM2.5-1.2B-Instruct

    LiquidAI·Chat

    ≈1.4 GB

    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 lfm1.0
    107.8KJan 2026gguf
    • Same category
    • Similar size (1.2B vs 2B)
    vs
  12. ibm-granite logo

    granite-3.3-2b-instruct

    ibm-granite·Chat

    ≈2.6 GB

    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 2.0
    41.1KApr 2025ollama
    • Same category
    • Similar size (2.5B vs 2B)
    • Commercial use OK
    vs
  13. LiquidAI logo

    LFM2-2.6B-Longevity

    LiquidAI·Chat

    ≈2.5 GB

    Longevity-LLM (L-LLM) is a family of compact, domain-adapted language models for interpreting heterogeneous aging biology data. Longevity LFMs are available in two sizes:

    2.6B125K ctx lfm1.0
    2KMay 2026gguf
    • Same category
    • Similar size (2.6B vs 2B)
    vs
  14. openbmb logo≈2.5 GB

    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 licence
    2.1KSept 2026
    • Same category
    • Similar size (2.8B vs 2B)
    vs
  15. Nanbeige logo

    Nanbeige4.2-3B

    Nanbeige·Chat

    ≈3.7 GB

    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 2.0
    93.2KJul 2026gguf
    • Same category
    • Larger (4.2B vs 2B)
    • Commercial use OK
    vs
  16. allenai logo≈1.9 GB

    OLMo 2 1B Instruct April 2025 is post-trained variant of the allenai/OLMo-2-0425-1B-RLVR1 model, which has undergone supervised finetuning on an OLMo-specific variant of the Tülu 3 dataset, further DPO training on this dataset, and final RLVR training on this dataset.

    1.5B4K ctx Apache 2.0
    60.6KApr 2025gguf
    • Same category
    • Similar size (1.5B vs 2B)
    • Commercial use OK
    vs
  17. ByteDance logo

    Ouro-1.4B

    ByteDance·Chat

    ≈2.9 GB

    Ouro-1.4B is a 1.4 billion parameter Looped Language Model (LoopLM) that achieves exceptional parameter efficiency through iterative shared-weight computation.

    1.4B64K ctx Apache 2.0
    20.5KOct 2025gguf
    • Same category
    • Similar size (1.4B vs 2B)
    • Commercial use OK
    vs
  18. ByteDance logo

    Ouro-2.6B

    ByteDance·Chat

    ≈5.1 GB

    Ouro-2.6B is a 2.6 billion parameter Looped Language Model (LoopLM) that achieves exceptional parameter efficiency through iterative shared-weight computation.

    2.7B64K ctx Apache 2.0
    10.5KOct 2025gguf
    • Same category
    • Similar size (2.7B vs 2B)
    • Commercial use OK
    vs
  19. WeiboAI logo

    VibeThinker-1.5B

    WeiboAI·Chat

    ≈1.8 GB

    VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium.

    1.8B128K ctx MIT
    2.7KNov 2025gguf
    • Same category
    • Similar size (1.8B vs 2B)
    • Commercial use OK
    vs
  20. HuggingFaceTB logo

    SmolLM3-3B-Base

    HuggingFaceTB·Chat

    ≈2.9 GB

    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 2.0
    87.3KJun 2025gguf
    • Same category
    • Similar size (3.1B vs 2B)
    • Commercial use OK
    vs
  21. XHToken logo

    Spark-X2.6-4B

    XHToken·Chat

    ≈4.1 GB

    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 2.0
    30KOct 2026gguf
    • Same category
    • Larger (4.1B vs 2B)
    • Commercial use OK
    vs
  22. CohereLabs logo

    tiny-aya-global

    CohereLabs·Chat

    ≈3.1 GB

    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 4.0
    28KFeb 2026gguf
    • Same category
    • Similar size (3.3B vs 2B)
    vs
  23. katanemo logo

    Arch-Router-1.5B

    katanemo·Chat

    ≈1.6 GB

    With the rapid proliferation of large language models (LLMs) -- each optimized for different strengths, style, or latency/cost profile -- routing has become an essential technique to operationalize the use of different models.

    1.5B32K ctx katanemo-research
    25.1KMay 2025gguf
    • Same category
    • Similar size (1.5B vs 2B)
    vs
  24. meta-llama logo

    Llama-3.2-1B-Instruct

    meta-llama·Chat

    ≈1.5 GB

    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 License
    1.3MSept 2024ollama
    • Same category
    • Similar size (1.2B vs 2B)
    vs