whatmodel.sh / FireFunction v2 (70B)

FireFunction v2 (70B)

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

FireFunction v2 (70B) is an open-weights language model from Fireworks AI, released June 2024. Its published size is 70.55B parameters. Licence: llama3.

Catalogue identity notes

fireworks-ai/llama-3-firefunction-v2 @7954e12 (created 2024-06-05, licence llama3). Fireworks AI function-calling fine-tune of Llama 3 70B (June 2024). Independent row: BFCL v3 (2025-06-14 snapshot).

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 70,553,706,496 parameters.

50.2±6.4#437 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 FireFunction v2 (70B), out of 1132 with a score, then more from Fireworks AI.

#modelscorewhereRAMreleased
566EXAONE 3.5 7.8B Instruct LG AI Research50±4local~6.1GB2024-12
567EXAONE Deep 2.4B LG AI Research50±2local~3.2GB2025-03
568FireFunction v2 (70B) Fireworks AI50±6local~24GB2024-06
569Mellum2 12B-A2.5B Instruct JetBrains50±2local~8.6GB2026-05
570Arch-Agent-1.5B Katanemo50±5local~2.4GB2025-06
more from Fireworks AI
841FireFunction v1 Fireworks AI42±6local~100GB2024-02

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▄▄▃▂▁ #272 of 334 * · 82% of its score · 1 test

Beats DeepSeek R1 0528 Qwen3 8B, Magistral Small 1.0 (2506), Llama 3.3 70B Instruct here, though they rank higher overall. Trails Granite 4.0 1B, SmolLM3 3B, Phi-3.5-mini-instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL v352.3% ✎▁▁▁▁▁▃▅█▅▄▁▁ beats 45/114medium · avg 52%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 82%blunt · at its level

$ 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 FireFunction v2 (70B) · needs ~42.5 GB · from huggingface.co/MaziyarPanahi
    chat in the terminal
    llama cli -hf MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf MaziyarPanahi/firefunction-v2-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 FireFunction v2 (70B) · needs ~42.5 GB · from huggingface.co/MaziyarPanahi

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/MaziyarPanahi/firefunction-v2-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 FireFunction v2 (70B) · needs ~40 GB · from ollama.com
    chat in the terminal
    ollama run firefunction-v2:70b

Official weights and documentation: huggingface.co/fireworks-ai ↗

$ how the score was worked out · Berkeley Function Calling Lea… 82%

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
Berkeley Function Calling Leaderboard result archive1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 82%Apache-2.0
prior · pull toward the middle▇▇▇▇▇ 18%
weighted average= 50.2

$ 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