GGUF quantizations of
IFM/K2-Horizon-7B
, a 7B dense decoder-only model for reasoning, coding, long-context work, and tool use. The source checkpoint supports a native context length of
524,288 tokens (512K)
.
Benchmarks
Benchmark results reported by IFM for the original K2-Horizon-7B checkpoint.
The files are text-only GGUFs; no vision projector is required. An upstream
chat_template.jinja
is included for clients that need an external chat template. SHA-256 checksums are provided in
SHA256SUMS.txt
.
Usage
Use a current
llama.cpp
build. The example below uses a practical 128K context;
-c 524288
can be used when the available memory is sufficient.
K2-Horizon-7B-GGUF huggingface.co is an AI model on huggingface.co that provides K2-Horizon-7B-GGUF's model effect (), which can be used instantly with this abenzerps K2-Horizon-7B-GGUF model. huggingface.co supports a free trial of the K2-Horizon-7B-GGUF model, and also provides paid use of the K2-Horizon-7B-GGUF. Support call K2-Horizon-7B-GGUF model through api, including Node.js, Python, http.
K2-Horizon-7B-GGUF huggingface.co is an online trial and call api platform, which integrates K2-Horizon-7B-GGUF's modeling effects, including api services, and provides a free online trial of K2-Horizon-7B-GGUF, you can try K2-Horizon-7B-GGUF online for free by clicking the link below.
abenzerps K2-Horizon-7B-GGUF online free url in huggingface.co:
K2-Horizon-7B-GGUF is an open source model from GitHub that offers a free installation service, and any user can find K2-Horizon-7B-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of K2-Horizon-7B-GGUF install, users can directly use K2-Horizon-7B-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.