LocalClaw/LLM/K2-Horizon-7B
Open-weight local LLM

K2-Horizon-7B

Catalogue summary: IFM Apache 2.0 dense K2 Horizon release with about 9B parameters, 128K context, open training-data references and an official BF16 GGUF artifact for K2 Horizon llama.cpp-compatible local experiments.

Repository editorial metadata; verify comparative claims in the linked upstream material.

24 GB catalogue minimum24 GB RAMBF16 GGUFCoding assistant
Choose an app

This model needs a special runtime. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
UnslothNot available for this model
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloads
llama.cppNot available for this model
Use with LocalClawOptional workspace after the model is installed
This model needs its official runtimeK2 Horizon llama.cpp fork / pending upstream llama.cpp support
Parameters
9B
Minimum RAM
24 GB
Model size
16.8 GB
Quantization
BF16 GGUF

Can K2-Horizon-7B run locally?

K2-Horizon-7B has a catalogue minimum of 24 GB RAM with BF16 GGUF. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use the official K2 Horizon llama.cpp fork / pending upstream llama.cpp support setup. The current low-bit files are not a stock LM Studio install.

Model sourcePublic GGUF repository (verified 2026-09-23): IFM/K2-Horizon-7B-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningstandardlong-contextgeneral

Install path

01
Check RAM fitMinimum 24 GB RAM. Start with the BF16 GGUF quant.
02
Load the modelFollow the official K2 Horizon llama.cpp fork / pending upstream llama.cpp support instructions. Stock LM Studio support is not confirmed.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: k2-horizon
  • Parameters: 9B
  • Recommended quantization: BF16 GGUF
  • Catalogue minimum RAM: 24 GB
  • Catalogue model size: 16.8 GB
  • Tags: chat, code, reasoning, standard, long-context, general

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • standard
  • long-context
  • general

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
7
quality
8
coding
8
reasoning
8

Technical notes

Developer
IFM
License
Apache 2.0
Context window
131,072 tokens
Architecture
Dense K2 Horizon decoder-only model with about 9B parameters, YaRN RoPE scaling and a 128K-token context window.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Comfortable headroomMac mini M4 Pro 48GBMobile workstationMacBook Pro M4 Max 36GBPower-user picks32GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

K2-Horizon-3.7B 3.7BK2-Horizon-32B 32B denseK2-Horizon-0.9B 0.9BK2-Horizon-MoVA-36B-A4B 36B (4B active, MoE)Ornith-1.5-9B 9BSpark-X2.5-4B 4BNemotron Nano 9B v2 9BGranite 3.3 (8B Instruct) 8B

Where to go next