LocalClaw/LLM/K2-Horizon-0.9B
Open-weight local LLM

K2-Horizon-0.9B

Catalogue summary: IFM Apache 2.0 compact dense K2 Horizon model with 128K context, multi-teacher distillation for math/code/STEM tasks, and an official BF16 GGUF path for llama.cpp-compatible local experiments.

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

8 GB catalogue minimum8 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
0.9B
Minimum RAM
8 GB
Model size
2.1 GB
Quantization
BF16 GGUF

Can K2-Horizon-0.9B run locally?

K2-Horizon-0.9B has a catalogue minimum of 8 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 2026-09-07): IFM/K2-Horizon-0.9B-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoninglightlong-contextgeneral

Install path

01
Check RAM fitMinimum 8 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: 0.9B
  • Recommended quantization: BF16 GGUF
  • Catalogue minimum RAM: 8 GB
  • Catalogue model size: 2.1 GB
  • Tags: chat, code, reasoning, light, 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
  • light
  • long-context
  • general

Capability profile

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

speed
9
quality
6
coding
6
reasoning
7

Technical notes

Developer
IFM
License
Apache 2.0
Context window
131,072 tokens
Architecture
0.9B-class dense decoder-only K2 Horizon model with YaRN RoPE scaling for 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.

Entry laptop fitMacBook Air 8GBMore headroomMac mini M4 16GBAll compatible picks8GB RAM guide

Related catalogue entries

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

K2-Horizon-MoVA-36B-A4B 36B (4B active, MoE)LFM2.5-2.6B 2.7BLing-3.0-tiny 7.9B (1.3B active, MoE)Spark-X2.5-1.7B 1.7BMiniCPM5 2B 2BAgents-A1 4B 4BGranite 4.2 (3B) 3BNanbeige4.2 3B 4B (3B non-embedding)

Where to go next