vLLM/Recipes
IFM

IFM/K2-Horizon-375B

Frontier-scale sparse MoE model for long-context research and high-capacity serving

379.17B stored parameters including embeddings / 26.67B active parameters per token

View on HuggingFace
moe379.17B / 26.67B524,288 ctxvLLM +text
Guide

Overview

K2-Horizon-375B is a frontier-scale mixture-of-expert (MoE) model in the IFM K2-Horizon family, with 379.17B stored parameters including embeddings, 26.67B active parameters per token, and support for up to 524,288 tokens of context.

K2-Horizon is an open-weight IFM model family built for transparent foundation-model research, staged checkpoint analysis, and practical deployment. The series spans compact dense models for local experimentation, dense mid-size and large models for high-quality research workloads, and mixture-of-expert (MoE) models such as K2-Horizon-375B for frontier-scale research and higher-capacity serving.

Launch Commands

vllm serve IFM/K2-Horizon-375B \
  --tensor-parallel-size 8 \
  --trust-remote-code \
  --dtype bfloat16 \
  --max-model-len 131072 \
  --reasoning-parser k2_horizon \
  --enable-auto-tool-choice \
  --tool-call-parser k2_horizon

Client usage

from openai import OpenAI

client = OpenAI(
    api_key="EMPTY", base_url="http://localhost:8000/v1", timeout=3600
)

resp = client.chat.completions.create(
    model="IFM/K2-Horizon-375B",
    messages=[{"role": "user", "content": "Give me three primes above 100."}],
    temperature=1.0, top_p=0.95, max_tokens=2048,
)
print(resp.choices[0].message.content)

Thinking modes

The model supports selectable thinking through chat_template_kwargs, per request or server-wide via --default-chat-template-kwargs:

  • {"reasoning_effort": "high"} — full thinking (default).
  • {"reasoning_effort": "medium"} — faster thinking.
  • {"reasoning_effort": "low"} — fastest thinking.

References