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 lumi-4b

120 open-weight models that do the same job as lumi-4b (4B 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
ceia-br logo

lumi-4b

ceia-br·Chat

≈4.2 GB

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 licence
4.1KOct 2026gguf
--vram
any
--gpus
--quant
  1. tomg-group-umd logo

    huginn-0125

    tomg-group-umd·Chat

    ≈4.1 GB

    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 2.0
    20.7KJan 2025
    • Same category
    • Similar size (3.9B vs 4B)
    • Commercial use OK
    vs
  2. ibm-granite logo≈3.0 GB

    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 2.0
    114.9KDec 2024gguf
    • Same category
    • Similar size (3.3B vs 4B)
    • Commercial use OK
    vs
  3. ornith-ai logo

    Ornith-1.5-9B

    ornith-ai·Chat

    ≈7.2 GB

    Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.

    9.7B256K ctx MIT
    570.4KAug 2026ollama
    • Same category
    • Larger (9.7B vs 4B)
    • Commercial use OK
    vs
  4. Qwen logo

    Qwen3-1.7B

    Qwen·Chat

    ≈2.6 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.

    2B40K ctx Apache 2.0
    3MApr 2025ollama
    • Same category
    • Similar size (2B vs 4B)
    • Commercial use OK
    • Widely used
    vs
  5. ibm-granite logo

    granite-swash-3b-a600m

    ibm-granite·Chat

    ≈2.5 GB

    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 2.0
    3KJul 2026gguf
    • Same category
    • Similar size (3B vs 4B)
    • Commercial use OK
    vs
  6. CohereLabs logo

    tiny-aya-base

    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
    2.9KFeb 2026gguf
    • Same category
    • Similar size (3.3B vs 4B)
    vs
  7. WeiboAI logo

    VibeThinker-3B

    WeiboAI·Chat

    ≈2.6 GB

    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 MIT
    2.6KJun 2026gguf
    • Same category
    • Similar size (3.1B vs 4B)
    • Commercial use OK
    vs
  8. 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
    2.2KSept 2026
    • Same category
    • Similar size (2.8B vs 4B)
    vs
  9. openbmb logo

    BitCPM-CANN-3B

    openbmb·Chat

    ≈2.5 GB

    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 2.0
    3KMay 2026gguf
    • Same category
    • Similar size (3B vs 4B)
    • Commercial use OK
    vs
  10. openbmb logo

    MiniCPM5-2B-SFT

    openbmb·Chat

    ≈2.3 GB

    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 2.0
    6.6KAug 2026
    • Same category
    • Similar size (2.5B vs 4B)
    • Commercial use OK
    vs
  11. ai21labs logo

    AI21-Jamba2-3B

    ai21labs·Chat

    ≈2.4 GB

    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 2.0
    6.6KJan 2026gguf
    • Same category
    • Similar size (3B vs 4B)
    • Commercial use OK
    vs
  12. arcee-ai logo

    AFM-4.5B

    arcee-ai·Chat

    ≈3.8 GB

    AFM-4.5B is a 4.5 billion parameter instruction-tuned model developed by Arcee.ai, designed for enterprise-grade performance across diverse deployment environments from cloud to edge.

    4.6B64K ctx Apache 2.0
    7.1KJul 2025gguf
    • Same category
    • Similar size (4.6B vs 4B)
    • Commercial use OK
    vs
  13. Qwen logo

    Qwen2.5-3B

    Qwen·Chat

    ≈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
    218.8KSept 2024gguf
    • Same category
    • Similar size (3.1B vs 4B)
    vs
  14. LiquidAI logo

    LFM3-1.7B

    LiquidAI·Chat

    ≈1.9 GB

    LFM3-1.7B is a text model for local agents and specialized applications, based on our new tri-hybrid architecture.

    1.7B256K ctx lfm1.0
    103.7KOct 2026ollama
    • Same category
    • Smaller (1.7B vs 4B)
    vs
  15. janhq logo≈4.2 GB

    Jan-v3-4B-base-instruct is a 4B-parameter model obtained via post-training distillation from a larger teacher, transferring capabilities while preserving general-purpose performance on standard benchmarks.

    4.4B256K ctx Apache 2.0
    1.1KJan 2026gguf
    • Same category
    • Similar size (4.4B vs 4B)
    • Commercial use OK
    vs
  16. openbmb logo≈2.3 GB

    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 2.0
    4.8KSept 2026
    • Same category
    • Similar size (2.5B vs 4B)
    • Commercial use OK
    vs
  17. Qwen logo≈5.5 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:

    7.6B32K ctx Apache 2.0
    6.5MSept 2024ollama
    • Same category
    • Similar size (7.6B vs 4B)
    • Commercial use OK
    • Widely used
    vs
  18. CohereLabs logo

    tiny-aya-l2-thinker

    CohereLabs·Chat

    ≈3.1 GB

    Cohere Labs Tiny Aya L2-Thinker is an open-weights research release of a 3.35 billion parameter multilingual reasoning model optimized to think in the same language as the user prompt before writing the final answer.

    3.4BCC BY-NC 4.0
    330Sept 2026
    • Same category
    • Similar size (3.4B vs 4B)
    vs
  19. NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 is a small language model (SLM) further post-trained from Gemma-4-E4B-it by NVIDIA. This is the full-precision (BF16) release.

    8B64K ctx openmdw-1.1
    29.7KOct 2026gguf
    • Same category
    • Larger (8B vs 4B)
    • Commercial use OK
    vs
  20. ai9stars logo

    G9v3-3B

    ai9stars·Chat

    ≈2.7 GB

    G9v3-3B is a dense 3B causal language model from the AI9Stars team, built for local deployment and resource-constrained scenarios. It targets everyday assistant use, coding, tool-use workflows, and reasoning tasks where a compact model is preferred.

    3B128K ctx Apache 2.0
    1.2KJul 2026gguf
    • Same category
    • Similar size (3B vs 4B)
    • Commercial use OK
    vs
  21. CohereLabs logo

    tiny-aya-fire

    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
    1.4KFeb 2026gguf
    • Same category
    • Similar size (3.3B vs 4B)
    vs
  22. allenai logo

    Olmo-3-7B-Instruct

    allenai·Chat

    ≈8.8 GB

    We introduce Olmo 3, a new family of 7B and 32B models both Instruct and Think variants. Long chain-of-thought thinking improves reasoning tasks like math and coding.

    7.3B64K ctx Apache 2.0
    128.7KNov 2025ollama
    • Same category
    • Similar size (7.3B vs 4B)
    • Commercial use OK
    vs
  23. ibm-granite logo

    granite-4.0-micro-base

    ibm-granite·Chat

    ≈3.1 GB

    Model Summary: Granite-4.0-Micro-Base is a decoder-only, long-context language model designed for a wide range of text-to-text generation tasks. It also supports Fill-in-the-Middle (FIM) code completion through the use of specialized prefix and suffix tokens.

    3.4B128K ctx Apache 2.0
    3.2KSept 2025gguf
    • Same category
    • Similar size (3.4B vs 4B)
    • Commercial use OK
    vs
  24. nvidia logo≈4.2 GB

    Llama-3.1-Nemotron-Nano-4B-v1.1 is a large language model (LLM) which is a derivative of nvidia/Llama-3.1-Minitron-4B-Width-Base, which is created from Llama 3.1 8B using our LLM compression technique and offers improvements in model accuracy and efficiency.

    4.5B128K ctx NVIDIA Open Model License
    6.6KMay 2025gguf
    • Same category
    • Similar size (4.5B vs 4B)
    • Commercial use OK
    vs