Downloads · 30 days
168
17% of all-time downloads
K2-Horizon-7B-GGUF
darioooooo0o/K2-Horizon-7B-GGUF
K2-Horizon-7B-GGUF is a text generation model from darioooooo0o. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as apache-2.0.
All-time downloads
997
Public
Repo size
31.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf31.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026
- SHA
- 55b20885
Try a prompt
Base models
Model card
From the Hugging Face model README
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 8192
Fits 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.
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026