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 plamo-3-8b-fin-instruct

120 open-weight models that do the same job as plamo-3-8b-fin-instruct (8.5B 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
pfnet logo≈6.1 GB

PLaMo-3-8B-Fin-Instruct is a Japanese language model for the financial domain, developed by Preferred Networks, Inc. It is fine-tuned from a PLaMo-3 base model through continued pre-training on financial corpora followed by supervised fine-tuning and direct preference optimization.

8.5B256K ctx plamo-community-license
878Nov 2026gguf
--vram
any
--gpus
--quant
  1. NousResearch logo

    Meta-Llama-3.1-8B-Instruct

    NousResearch·Chat

    ≈6.3 GB

    The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out).

    8B128K ctx Llama 3.1 Community License
    134.1KJul 2024gguf
    • Same category
    • Similar size (8B vs 8.5B)
    vs
  2. Qwen logo≈5.5 GB

    Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 7B Qwen2 model.

    7.6B32K ctx Apache 2.0
    311.6KJun 2024ollama
    • Same category
    • Similar size (7.6B vs 8.5B)
    • Commercial use OK
    vs
  3. Qwen logo

    Qwen2-7B

    Qwen·Chat

    ≈5.5 GB

    Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the 7B Qwen2 base language model.

    7.6B128K ctx Apache 2.0
    298.2KJun 2024gguf
    • Same category
    • Similar size (7.6B vs 8.5B)
    • Commercial use OK
    vs
  4. allenai logo≈8.7 GB

    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.

    7.4B32K ctx Apache 2.0
    2.8KFeb 2026
    • Same category
    • Similar size (7.4B vs 8.5B)
    • Commercial use OK
    vs
  5. zai-org logo

    GLM-4-9B-0414

    zai-org·Chat

    ≈6.4 GB

    The GLM family welcomes new members, the GLM-4-32B-0414 series models, featuring 32 billion parameters. Its performance is comparable to OpenAI’s GPT series and DeepSeek’s V3/R1 series. It also supports very user-friendly local deployment features.

    9.4B32K ctx MIT
    22KApr 2025ollama
    • Same category
    • Similar size (9.4B vs 8.5B)
    • Commercial use OK
    vs
  6. openbmb logo

    MiniCPM4-8B

    openbmb·Chat

    ≈5.6 GB

    MiniCPM4 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.

    8.2B32K ctx Apache 2.0
    7.8KJun 2025gguf
    • Same category
    • Similar size (8.2B vs 8.5B)
    • Commercial use OK
    vs
  7. openbmb logo

    MiniCPM4-MCP

    openbmb·Chat

    ≈5.6 GB

    MiniCPM4 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.

    8.2B32K ctx Apache 2.0
    7.9KJun 2025gguf
    • Same category
    • Similar size (8.2B vs 8.5B)
    • Commercial use OK
    vs
  8. stepfun-ai logo

    PaCoRe-8B

    stepfun-ai·Chat

    ≈6.5 GB

    We introduce PaCoRe (Parallel Coordinated Reasoning), a framework that shifts the driver of inference from sequential depth to coordinated parallel breadth, breaking the model context limitation and massively scaling test time compute: Think in Parallel: PaCoRe launches massive parallel exploration…

    8.2B320K ctx MIT
    1.9KDec 2025gguf
    • Same category
    • Similar size (8.2B vs 8.5B)
    • Commercial use OK
    vs
  9. XiaomiMiMo logo

    MiMo-7B-Base

    XiaomiMiMo·Chat

    ≈6.3 GB

    Currently, most successful RL works, including open-source research, rely on relatively large base models, e.g., 32B models, particularly for enhancing code reasoning capabilities.

    7.8B32K ctx MIT
    14.7KApr 2025
    • Same category
    • Similar size (7.8B vs 8.5B)
    • Commercial use OK
    vs
  10. ibm-granite logo

    granite-3.1-8b-instruct

    ibm-granite·Chat

    ≈6.6 GB

    Model Summary: Granite-3.1-8B-Instruct is a 8B parameter long-context instruct model finetuned from Granite-3.1-8B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets tailored for solving long context problems.

    8.2B128K ctx Apache 2.0
    29.7KDec 2024gguf
    • Same category
    • Similar size (8.2B vs 8.5B)
    • Commercial use OK
    vs
  11. ibm-granite logo≈7.5 GB

    Model Summary: Granite Switch 4.1 8B Preview is a modular LLM built on IBM Granite 4.1 8B with embedded adapters from the Granite Libraries collection.

    9.6B128K ctx Apache 2.0
    1.1KMay 2026
    • Same category
    • Similar size (9.6B vs 8.5B)
    • Commercial use OK
    vs
  12. google logo≈4.6 GB

    T5Gemma is a family of lightweight yet powerful encoder-decoder research models from Google. These models are created by adapting pretrained decoder-only models into a encoder-decoder.

    5.6B8K ctx Gemma Terms of Use
    180.8KJun 2025
    • Same category
    • Similar size (5.6B vs 8.5B)
    vs
  13. mistralai logo≈5.8 GB

    The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.

    7.2B32K ctx Apache 2.0
    1.3MDec 2023ollama
    • Same category
    • Similar size (7.2B vs 8.5B)
    • Commercial use OK
    vs
  14. Qwen logo≈4.0 GB

    We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements:

    4B256K ctx Apache 2.0
    2.6MAug 2025gguf
    • Same category
    • Smaller (4B vs 8.5B)
    • Commercial use OK
    • Widely used
    vs
  15. tokyotech-llm logo≈6.3 GB

    Llama 3.1 Swallow is a series of large language models (8B, 70B) that were built by continual pre-training on the Meta Llama 3.1 models. Llama 3.1 Swallow enhanced the Japanese language capabilities of the original Llama 3.1 while retaining the English language capabilities.

    8B128K ctx Llama 3.3 Community License
    7.3KJun 2025gguf
    • Same category
    • Similar size (8B vs 8.5B)
    vs
  16. IFM logo≈4.6 GB

    K2-Horizon-3.7B is the small dense member of the K2-Horizon family: a 3.7B-core decoder-only model with a 512K context window.

    5.1B512K ctx Apache 2.0
    15.5KSept 2026gguf
    • Same category
    • Similar size (5.1B vs 8.5B)
    • Commercial use OK
    vs
  17. microsoft logo

    UserLM-8b

    microsoft·Chat

    ≈6.3 GB

    Unlike typical LLMs that are trained to play the role of the "assistant" in conversation, we trained UserLM-8b to simulate the “user” role in conversation (by training it to predict user turns in a large corpus of conversations called WildChat).

    8B8K ctx MIT
    2.6KSept 2025gguf
    • Same category
    • Similar size (8B vs 8.5B)
    • Commercial use OK
    vs
  18. ibm-granite logo≈7.0 GB

    Model Summary: Granite-4.1-8B-LLMON-preview is an 8B-parameter instruct model fine-tuned from Granite-4.1-8B-base to consume prompts in LLMON (LLM Object Notation) instead of a conventional chat template.

    8.8B128K ctx Apache 2.0
    126Oct 2026
    • Same category
    • Similar size (8.8B vs 8.5B)
    • Commercial use OK
    vs
  19. google logo

    gemma-2-9b-it

    google·Chat

    ≈8.6 GB

    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.

    9.2B8K ctx Gemma Terms of Use
    102.2KJun 2024ollama
    • Same category
    • Similar size (9.2B vs 8.5B)
    vs
  20. 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
    96.9KJul 2026gguf
    • Same category
    • Smaller (4.2B vs 8.5B)
    • Commercial use OK
    vs
  21. allenai logo≈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
    3.7KNov 2025gguf
    • Same category
    • Similar size (7.3B vs 8.5B)
    • Commercial use OK
    vs
  22. ByteDance-Seed logo

    academic-ds-9B

    ByteDance-Seed·Chat

    ≈7.5 GB

    This is a 9B model whose architecture is deepseek-v3, trained from scratch using 350B+ tokens from fully open-source, English-only datasets. It is designed for development and debugging purposes within the open-source community.

    9.4BA1.6B8K ctx Apache 2.0
    11.4KApr 2025gguf
    • Same category
    • Similar size (9.4B vs 8.5B)
    • Commercial use OK
    vs
  23. K-intelligence logo

    Midm-2.0-Base-Instruct

    K-intelligence·Chat

    ≈8.8 GB

    Mi:dm 2.0 is a "Korea-centric AI" model developed using KT's proprietary technology. The term "Korea-centric AI" refers to a model that deeply internalizes the unique values, cognitive frameworks, and commonsense reasoning inherent to Korean society.

    11.5B32K ctx MIT
    39.6KJul 2025gguf
    • Same category
    • Similar size (11.5B vs 8.5B)
    • Commercial use OK
    vs
  24. nvidia logo≈6.5 GB

    We're excited to introduce Nemotron-Cascade-8B, a powerful general-purpose model trained through sequential and domain-wise reinforcement learning. Nemotron-Cascade-8B is post-trained from the Qwen3-8B-Base model.

    8.2B32K ctx NVIDIA Open Model License
    1.1KDec 2025gguf
    • Same category
    • Similar size (8.2B vs 8.5B)
    • Commercial use OK
    vs