K2 Horizon MoVA 36B A4B

K2 Horizon MoVA 36B A4B from IFM. Source-based hardware guidance from its published configuration.

EstimatedRepository opened Sep 1, 2026Source checked 9/23/2026Version: e9f33cb4

LOCALRENTED GPUOPEN WEIGHTS

At a glance

Parameters: 37.44B
Architecture: k2_horizon
Context length: 524,288
License: apache-2.0
Software: vLLM, Transformers

View the model source

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Ways to run it

vLLM · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

vllm serve IFM/K2-Horizon-MoVA-36B-A4B  --revision main  --tensor-parallel-size 2  --enable-expert-parallel  --trust-remote-code  --dtype bfloat16  --reasoning-parser k2_horizon  --tool-call-parser k2_horizon  --enable-auto-tool-choice

Official instructions

Transformers · See official guide

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "IFM/K2-Horizon-MoVA-36B-A4B"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, device_map="auto", dtype="bfloat16", low_cpu_mem_usage=True, trust_remote_code=True
)

inputs = tokenizer("Explain why long-context evaluation is difficult.", return_tensors="pt").to(model.device)
inputs.pop("token_type_ids", None)
outputs = model.generate(**inputs, max_new_tokens=32768, temperature=1.0, top_p=0.95, do_sample=True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Official instructions

Explore its uses

SAFETENSORSTEXT-GENERATION

Keep exploring

Text

Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

MODEL SIZE27.36B

LOCALRENTED GPU

Released Sep 17, 2026

Text

DeepSeek

DeepSeek V4.1 Flash

A multimodal reasoning model with a compressed key-value cache, published as open weights.

LOCALRENTED GPU

Repository opened Sep 10, 2026

Text

Qwen

Qwen3.8-Flash-Next

An experimental open-weight multimodal model with sparse attention and 262K native context.

MODEL SIZE125B language · 6B active

LOCALRENTED GPU

Repository opened Aug 24, 2026