darioooooo0o/K2-Horizon-7B-GGUF overview
K2 Horizon 7B GGUF quants X https://img.shields.io/badge/X Follow 000000?logo=x&logoColor=white https://x.com/imdariotoo Requests, questions or suggestions? Me…
Runs locally from ~4.32 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | darioooooo0o/K2-Horizon-7B-GGUF |
|---|---|
| Author | darioooooo0o |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | IFM/K2-Horizon-7B |
| Last modified | 2026-09-03T19:06:59.000Z |
Model README
---
license: apache-2.0
base_model: IFM/K2-Horizon-7B
pipeline_tag: text-generation
library_name: gguf
tags:
- k2-horizon
- llama.cpp
- gguf
- k-quants
---
K2-Horizon-7B GGUF quants
Requests, questions or suggestions? Message me on X: https://x.com/imdariotoo
GGUF quantizations of IFM/K2-Horizon-7B.
Converted with the official k2-official llama.cpp branch (MBZUAI-IFM port, commit 35999d101).
Files
| File | Quant | Size |
|---|---|---|
| k2horizon7-q3_k_m.gguf | Q3_K_M | ~4.3 GB |
| k2horizon7-q4_k_s.gguf | Q4_K_S | ~5.0 GB |
| k2horizon7-q4_k_m.gguf | Q4_K_M | ~5.2 GB |
| k2horizon7-q5_k_m.gguf | Q5_K_M | ~6.0 GB |
| k2horizon7-q8_0.gguf | Q8_0 | ~8.9 GB |
Requirements
Use a llama.cpp build from the k2-official branch of MBZUAI-IFM/llama.cpp (or anything that merges that port). Mainline llama.cpp does NOT support the k2-horizon architecture.
Usage
llama-cli -m k2horizon7-q4_k_m.gguf -ngl 99 -c 8192Fits entirely on an 8 GB+ GPU; no CPU offload needed.
Notes
- Plain K-quants from BF16, no imatrix.
- All quants verified loading and generating on RTX 3060 12GB.
Run darioooooo0o/K2-Horizon-7B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models