[!IMPORTANT] Compatibility: These GGUF files require a
llama.cppbuild with K2 Horizon architecture support. Until upstream support lands, use the MBZUAI-IFM fork.
K2-Horizon-7B GGUF
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.
GGUF files
| Quantization | File | Size |
|---|---|---|
| Q4_0 | K2-Horizon-7B-Q4_0.gguf | 5.34 GB |
| Q4_K_M | K2-Horizon-7B-Q4_K_M.gguf | 5.59 GB |
| Q4_K_M Selective | K2-Horizon-7B-Q4_K_M-Selective.gguf | 5.96 GB |
| Q5_K_M | K2-Horizon-7B-Q5_K_M.gguf | 6.47 GB |
| Q6_K | K2-Horizon-7B-Q6_K.gguf | 7.39 GB |
| Q8_0 | K2-Horizon-7B-Q8_0.gguf | 9.57 GB |
The files are text-only GGUFs; no vision projector is required. The selective variant uses a Q4_K_M baseline with attention Q/K/V/O projection tensors kept at Q6_K; it is a manual tensor-selective build and does not use an importance matrix. SHA-256 checksums are provided in SHA256SUMS.txt.
Chat template
Each GGUF embeds the llama.cpp-compatible chat template. chat_template.jinja is a matching external copy for tools that require one. The original source template is retained as chat_template.upstream.jinja for runtimes with full Jinja support.
xml is the default tool-call format. Use --chat-template-kwargs to select json or xml_typed when required.
Usage
Use the IFM K2 Horizon llama.cpp fork. The example below uses a practical 128K context; -c 524288 can be used when the available memory is sufficient.
llama-cli \
-m K2-Horizon-7B-Q4_K_M.gguf \
-c 131072 --jinja \
--temp 1.0 --top-p 0.95
Source
- Source model: IFM/K2-Horizon-7B
- Source revision:
2c9659a - Source license: Apache-2.0