F2LLM-v2-8B (codefuse-ai) specs, prices, where it runs and its benchmark standing

Name: F2LLM-v2-8B (codefuse-ai)
Author: Codefuse Ai

open weights · top 10 on 1 of 1 · released Mar 9, 2026

Provider: Codefuse Ai
Release date: Mar 9, 2026; Boards
Parameters: 7.6B total; Hugging Face
Modalities: Text to Embeddings; Hugging Face
License: Apache 2.0; Hugging Face
Hosting: self-host: weights on Hugging Face
Hardware: Estimate: about 15 GB of weights as published (BF16), about 7.6 GB at 8-bit, about 3.8 GB at 4-bit, plus memory for the context; Hugging Face config
Weights: Open weights
Benchmarks: 1 board captured

Rank	Board	Category	Score	Of	Over time
9	MTEBEmbeddings · as “codefuse-ai/F2LLM-v2-8B”	Embeddings	68.1%	96

Versions and release history

8 versions in this line since Mar 9, 2026, from Pricing, OpenRouter and the boards.

Version	Released	Source
F2LLM-v2-0.6B (codefuse-ai)	Mar 9, 20268 months ago	Boards
F2LLM-v2-1.7B (codefuse-ai)	Mar 9, 20268 months ago	Boards
F2LLM-v2-14B (codefuse-ai)	Mar 9, 20268 months ago	Boards
F2LLM-v2-160M (codefuse-ai)	Mar 9, 20268 months ago	Boards
F2LLM-v2-330M (codefuse-ai)	Mar 9, 20268 months ago	Boards
F2LLM-v2-4B (codefuse-ai)	Mar 9, 20268 months ago	Boards
F2LLM-v2-80M (codefuse-ai)	Mar 9, 20268 months ago	Boards
F2LLM-v2-8B (codefuse-ai)this model	Mar 9, 20268 months ago	Boards

Category ranks, more models and catalog changes