HO

K2 Horizon 0.9B meeting agent zh

HorizonGGUF by LuigiUpdated 2026-10-12
Download on Hugging Face
Parameters1.09B
Context128K
Layers28
Architecturellama
Smallest quant0.6 GB
Quick answer

K2 Horizon 0.9B meeting agent zh needs about 1.6 GB of memory at Q4_0 (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.6 GB (Q4_0) to 1.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

K2 Horizon 0.9B meeting agent (zh‑TW) – a reading‑agent for meeting transcripts

K2 Horizon 0.9B is a 1.09B‑parameter llama model fine‑tuned for reading and summarising zh‑TW meeting transcripts. It outputs short cited notes, a title and a prose summary. The model is released under apache‑2.0 and available as GGUF for llama.cpp.

Good at

  • Reading and summarising zh‑TW meeting transcripts
  • Producing cited notes and concise summaries
  • Operating within a 4k context window

Limits

  • No vision support
  • Requires a 4k context window
  • No system prompt support

Best for

  • Automated meeting note generation
  • Real‑time transcript summarisation
  • Generating concise meeting summaries

Who it’s for. Developers building meeting‑assistant tools or summarisation pipelines for zh‑TW. Researchers needing a specialised reading agent for Chinese meeting data.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.6 GB 1.6 GB
Fits Get file →
Q8_01.2 GB 2.1 GB
Fits Get file →

For 8GB VRAM use Q4_0 (0.65GB file, ~1.6GB memory at 8k context). For 16GB VRAM use Q8_0 (1.17GB file, ~2.1GB memory at 8k context). Memory estimates are approximate.

What GPU do you need for K2 Horizon 0.9B meeting agent zh?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q8_0 (1.2 GB file, about 2.1 GB in use).

Which K2 Horizon 0.9B meeting agent zh quant should you choose?

Q4_0 (0.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.09B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized byLuigi
FamilyHorizon
Licenseapache-2.0
Downloads (HF)912
Last updated2026-10-12

Frequently asked questions about K2 Horizon 0.9B meeting agent zh

How much VRAM does K2 Horizon 0.9B meeting agent zh need?

About 1.6 GB at Q4_0 with an 8K context window. That is the 0.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run K2 Horizon 0.9B meeting agent zh on an 8 GB GPU?

Yes, with Q8_0: the 1.2 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of K2 Horizon 0.9B meeting agent zh GGUF?

It depends on the quant: Q4_0 is 0.6 GB, Q8_0 is 1.2 GB.

What context length does K2 Horizon 0.9B meeting agent zh support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download K2 Horizon 0.9B meeting agent zh GGUF?

The files are on Hugging Face in the Luigi/K2-Horizon-0.9B-meeting-agent-zh-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does K2 Horizon 0.9B meeting agent zh use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the Q4_0 quantised file uses about 1.6GB of VRAM at 8k context, which fits within 8GB.

What license does the model use?

The model is released under the apache-2.0 license.

Does the model support vision or image input?

No, the model has no vision support and only processes text.

Similar models

Browse all →

More from Luigi

All by Luigi →

More Horizon models

All Horizon →

Other tiny models

All tiny models →