What are the hardware requirements for K2 Horizon 32B FP8?

K2 Horizon 32B FP8 requires approximately 37.4 GB of VRAM and supports a context window of 512K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed K2 Horizon 32B FP8 and how large is it?

K2 Horizon 32B FP8 is developed by IFM, a model with 32b 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 32B FP8?

K2 Horizon 32B FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

K2 Horizon 32B FP8 by IFM — VRAM 37.4GB, 512K context

Name: K2 Horizon 32B FP8
Author: IFM

K2 Horizon 32B FP8 is an open-source language model by IFM. Features: 32b LLM, VRAM: 37.4GB, Context: 512K, License: apache-2.0, LLM Explorer Score: 0.33.

32b Compressed-tensors Conversational Custom code Dataset:ifm/k2-horizon-midtrai... Dataset:ifm/k2-horizon-pretrai... Dense En Ifm K2-horizon K2 horizon Open-weights Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/IFM/K2-Horizon-32B-FP8

K2 Horizon 32B FP8 Parameters and Internals

LLM Name	K2 Horizon 32B FP8
Repository 🤗	https://huggingface.co/IFM/K2-Horizon-32B-FP8
Model Name	K2-Horizon-32B
Model Size	32b
Required VRAM	37.4 GB
Updated	2026-09-05
Maintainer	IFM
Model Type	k2_horizon
Model Files	19.9 GB: 1-of-2 17.5 GB: 2-of-2
Supported Languages	en
Model Architecture	K2HorizonForCausalLM
License	apache-2.0
Context Length	524288
Model Max Length	524288
Transformers Version	5.13.0
Tokenizer Class	TokenizersBackend
Vocabulary Size	250624

Rank the K2 Horizon 32B FP8 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 32B FP8

Best Alternatives	Context / RAM	Downloads	Likes
K2 Horizon 32B	512K / 42 GB	323	16

Note: green Score (e.g. "73.2") means that the model is better than IFM/K2-Horizon-32B-FP8.