What are the hardware requirements for K2 Horizon 7B Uno?

K2 Horizon 7B Uno requires approximately 1.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed K2 Horizon 7B Uno and how large is it?

K2 Horizon 7B Uno is developed by IFM, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate K2 Horizon 7B Uno?

K2 Horizon 7B Uno is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

K2 Horizon 7B Uno by IFM — VRAM 1.4GB

Name: K2 Horizon 7B Uno
Author: IFM

K2 Horizon 7B Uno is an open-source language model by IFM. Features: 7b LLM, VRAM: 1.4GB, License: apache-2.0, LLM Explorer Score: 0.42.

Arxiv:2609.04010 Adapter Base model:adapter:ifm/k2-hori... Base model:ifm/k2-horizon-7b Conditional-lora Diffusion-language-model Finetuned Lora Peft Region:us Safetensors Uno

Model Card on HF 🤗: https://huggingface.co/IFM/K2-Horizon-7B-Uno

K2 Horizon 7B Uno Parameters and Internals

LLM Name	K2 Horizon 7B Uno
Repository 🤗	https://huggingface.co/IFM/K2-Horizon-7B-Uno
Base Model(s)	K2 Horizon 7B IFM/K2-Horizon-7B
Model Size	7b
Required VRAM	1.4 GB
Updated	2026-09-05
Maintainer	IFM
Model Files	1.4 GB
Model Architecture	Adapter
License	apache-2.0
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	q_proj\|k_proj\|v_proj\|o_proj\|gate_proj\|down_proj\|up_proj
LoRA Alpha	8192
LoRA Dropout	0.05
R Param	128

Rank the K2 Horizon 7B Uno capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to K2 Horizon 7B Uno

Best Alternatives	Context / RAM	Downloads	Likes
...x H3 Prompt Rewriter LoRA Omni	0K / 1.3 GB	27	32
DeepMath R1 Distill Qwen 7B	0K / 0.1 GB	13	1
Llama2 7B Qlora Guanaco	0K / 0.1 GB	11	1
Qwen Megumin	0K / 0.1 GB	11	1
Mistral 7B Instruct Vi Alpaca	0K / 0.4 GB	5	0
...s 25 Mistral 7B Irca DPO Pairs	0K / 0.1 GB	6	0
Qwen1.5 7B Chat Sa V0.1	0K / 0 GB	8	0
Uk Fraud Chatbot Llama2	0K / 0.4 GB	6	0
Zephyr 7B Ipo 0K 15K I1	0K / 0.7 GB	5	0
Deepseek Llm 7B Chat Sa V0.1	0K / 0 GB	7	0