whatmodel.sh / InternLM3 8B Instruct

InternLM3 8B Instruct

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

InternLM3 8B Instruct is an open-weights language model from Shanghai AI Laboratory (InternLM), released January 2025. Its published size is 8.8B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo internlm/internlm3-8b-instruct @28c9941: licence tag apache-2.0. 8,804,241,408 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2025-01: month the maker's Hugging Face repo was created (createdAt 2025-01-13).

54.3±10.6#343 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of InternLM3 8B Instruct, out of 1132 with a score, then more from Shanghai AI Laboratory (InternLM).

#modelscorewhereRAMreleased
444Pixtral Large (2411) Mistral54±3local~51GB2024-11
445Bielik 11B v2.6 Instruct SpeakLeash54±3local~8.1GB2025-06
446InternLM3 8B Instruct Shanghai AI Laboratory (InternLM)54±11local~6.8GB2025-01
447Nova Premier Amazon54±2api $5.00/M2025-04
448Devstral Medium 1.0 (2507) Mistral54±3comparison only2025-07
more from Shanghai AI Laboratory (InternLM)
621InternLM2.5 7B Chat Shanghai AI Laboratory (InternLM)49±2local~6.1GB2024-06
678InternLM2.5 7B Chat 1M Shanghai AI Laboratory (InternLM)47±4local~6.4GB2024-06
723InternLM2.5 20B Chat Shanghai AI Laboratory (InternLM)46±2local~14GB2024-08

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 50% of its score
testresultvs the others in its rundifficultycountswhy
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)96.0% ✎▁▁▂▃▄▄█▆▃▂▂▁ beats 86/140very easy · avg 94%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%blunt · maxed out · noisy

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run InternLM3 8B Instruct · needs ~5.4 GB · from huggingface.co/internlm (official)
    chat in the terminal
    llama cli -hf internlm/internlm3-8b-instruct-gguf:q4_k_m
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf internlm/internlm3-8b-instruct-gguf:q4_k_m

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run InternLM3 8B Instruct · needs ~5.4 GB · from huggingface.co/internlm (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/internlm/internlm3-8b-instruct-gguf@q4_k_m -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run InternLM3 8B Instruct · needs ~5.4 GB · from huggingface.co/internlm (official)
    chat in the terminal
    ollama run hf.co/internlm/internlm3-8b-instruct-gguf:q4_k_m

MLX (Mac)

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run InternLM3 8B Instruct · needs ~5 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/internlm3-8b-instruct-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/internlm3-8b-instruct-4bit

Other ways to run it

  1. Run it as published · needs ~17.61 GB · from huggingface.co/internlm (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='internlm/internlm3-8b-instruct', torch_dtype='auto', device_map='auto', trust_remote_code=True)('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/internlm ↗

$ how the score was worked out · Vectara hallucination leaderb… 50%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%Apache-2.0
prior · pull toward the middle▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%
weighted average= 54.3

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json