LocalClaw/LLM/K2-Horizon-32B
Open-weight local LLM

K2-Horizon-32B

Catalogue summary: IFM Apache 2.0 dense K2 Horizon member with 32B parameters, 512K context, official Q4_K_M GGUF artifacts, and a documented local path through the K2 Horizon llama.cpp fork while upstream support matures.

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

32 GB catalogue minimum32 GB RAMQ4_K_MCoding 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
32B dense
Minimum RAM
32 GB
Model size
21.1 GB
Quantization
Q4_K_M

Can K2-Horizon-32B run locally?

K2-Horizon-32B has a catalogue minimum of 32 GB RAM with Q4_K_M. 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-32B-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningagenticlong-contextpowergeneral

Install path

01
Check RAM fitMinimum 32 GB RAM. Start with the Q4_K_M 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: 32B dense
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 32 GB
  • Catalogue model size: 21.1 GB
  • Tags: chat, code, reasoning, agentic, long-context, power, 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
  • agentic
  • long-context
  • power

Capability profile

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

speed
5
quality
9
coding
9
reasoning
9

Technical notes

Developer
IFM
License
Apache 2.0
Context window
524,288 tokens
Architecture
Dense K2 Horizon decoder-only model with 32B parameters, YaRN-style long-context support and a 512K-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-MoVA-36B-A4B 36B (4B active, MoE)K2-Horizon-7B 9BK2-Horizon-0.9B 0.9BNemotron 3.5 Lightning 30B-A3B 30B (3B active, MoE)Ornith-1.5-35B-A3B 35B (3B active, MoE)Nex-N2.5-mini 35B MoEOccamy-1.0 35B (3B active, MoE)

Where to go next