whatmodel.sh / NexusRaven V2 13B

NexusRaven V2 13B

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

NexusRaven V2 13B is an open-weights language model from Nexusflow, released December 2023. Its published size is 13.02B parameters and a 16k-token context window. Licence: other.

Catalogue identity notes

Nexusflow/NexusRaven-V2-13B @a6b84dc (created 2023-12-04, licence other). Nexusflow's function-calling model (Dec 2023, CodeLlama-13B base). Independent row: BFCL v3 (2025-06-14 snapshot).

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 13,016,110,080 parameters.

28.7±2.6#654 of 719 LLMsfrom 5 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of NexusRaven V2 13B, out of 828 with a score, then more from Nexusflow.

#modelscorewhereRAMreleased
751Granite 3.1 1B-A400M Instruct IBM29±2local~2.3GB2024-12
752OPT-30B Meta29±1local~64GB2022-05
753NexusRaven V2 13B Nexusflow29±3local~9.3GB2023-12
754OLMo 7B Allen Institute for AI28±1local~30GB2024-02
755Falcon 40B Instruct TII28±2local~27GB2023-05
more from Nexusflow
290Athene-V2-Chat 72B Nexusflow56±2local~44GB2024-11
401Athene-70B Nexusflow51±1local~29GB2024-07
626Starling-LM 7B beta Nexusflow40±1local~6GB2024-03

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #289 of 300 * · 11% of its score · 1 test

Beats QwQ-32B-Preview, DeepSeek-Coder-V2 Lite Instruct (16B-A2.4B), Phi-4-mini 3.8B here, though they rank higher overall. Trails Granite 4.0 350M, Granite 4.0 H 350M, ChatGLM3-6B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL v336.0% ✎▁▁▁▁▃▃▅█▅▄▁▁ beats 11/114medium · avg 52%▇▇▇▇▇ 11%blunt · at its level
other tests4 not in a task · 86% of its score
testresultvs the others in its rundifficultycountswhy
Natural Questions (closed book)14.2% ✎▁·▁·▁▂▁▂·▅▂█ beats 12/28medium · avg 58%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%typical
TriviaQA42.3% ✎▁··▁█▃▃▁▄▅▄█ beats 18/28easy · avg 79%▇▇▇▇ 10%at its level · noisy
TruthfulQA MC244.4% ✎▅▃█▆▁▂▅···▁▁ beats 18/31medium · avg 64%▇▇ 4.9%blunt · at its level
HaluEval QA hallucination detection (accuracy)23.7% ✎█▁▁·▁▁·▁▁▁▁▁ beats 12/27medium · avg 70%▇ 3.6%sharp · too hard for it · 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 NexusRaven V2 13B · needs ~7.9 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/NexusRaven-V2-13B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/NexusRaven-V2-13B-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 NexusRaven V2 13B · needs ~7.9 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/NexusRaven-V2-13B-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run NexusRaven V2 13B · needs ~7.4 GB · from ollama.com
    chat in the terminal
    ollama run nexusraven:13b

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 NexusRaven V2 13B · needs ~10.6 GB, Mac only · from huggingface.co/k8smee
    chat in the terminal
    mlx_lm.chat --model k8smee/NexusRaven-V2-13B-mlx-6Bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model k8smee/NexusRaven-V2-13B-mlx-6Bit

Official weights and documentation: huggingface.co/Nexusflow ↗

$ how the score was worked out · Hallucinations Leaderboard re… 86%, Berkeley Function Calling Lea… 11%

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
Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)4▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 86%Apache-2.0
Berkeley Function Calling Leaderboard result archive1▇▇▇ 11%Apache-2.0
prior · pull toward the middle▇ 3%
weighted average= 28.7

$ 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