Model library / IFM
K2-Horizon-375B-A23B is an open-weight sparse MiE language model from IFM with 379 B parameters, 23 B active per token and a 512 K context.
Mixture of experts, count not published
Context length in tokens, as published
Weights at the released precision
Licence declared on the repository
Overview
K2-Horizon-375B-A23B is a sparse mixture-of-experts language model released by IFM. The publisher positions it for agentic tool use, terminal interactions and long-horizon workflow tasks, leveraging a 512 K token context window. It aims to match or exceed the performance of larger open-weight models while remaining fully open, with training data, code and intermediate checkpoints to be released.
The model contains 379.2 billion parameters but activates roughly 23 billion per token thanks to its expert routing. It supports a native context of 524,288 tokens and is distributed in bfloat16 format. The code and weights are released under the Apache-2.0 licence, allowing commercial and research use.
Specification
| Repository | IFM/K2-Horizon-375B-A23B |
| Publisher | IFM |
| Published | 2 September 2026 |
| Architecture | K2HorizonForCausalLM |
| Model type | k2_horizon |
| Parameters | 379,167,159,168 |
| Layers | 61 |
| Hidden size | 6,144 |
| Attention heads | 48, 8 key/value heads |
| Context length | 524,288 tokens |
| Vocabulary | 250,624 tokens |
| Weight format | bfloat16 |
| Licence | apache-2.0 |
Memory
Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.
| Precision | Weights | Notes |
|---|---|---|
| bf16 | 706.3 GiB | Full precision as released |
| fp8 | 353.1 GiB | 8-bit, near-lossless on most models |
| int4 | 176.6 GiB | 4-bit, smallest footprint |
The cache costs 244 KiB per token at 16-bit, so the full 524,288-token context of one request needs about 122.0 GiB. Concurrency multiplies that number, not the weights.
Hardware
At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.
| GPU | Cards needed | Free for cache | Context it holds |
|---|---|---|---|
| RTX 4090 24GB | more than 8 | — | — |
| RTX 5090 32GB | more than 8 | — | — |
| L40S 48GB | more than 8 | — | — |
| A100 80GB | more than 8 | — | — |
| H100 80GB | more than 8 | — | — |
| RTX PRO 6000 96GB | more than 8 | — | — |
| H200 141GB | 8 | 288.9 GiB | the full 524,288 tokens |
Serving
A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.
vllm serve IFM/K2-Horizon-375B-A23B \ --tensor-parallel-size 8 \ --max-model-len 524288 \ --gpu-memory-utilization 0.90
Questions
The weights take about 706 GiB at the released precision. No single card in the table above holds that, so it needs several GPUs or a lower precision.
The repository declares apache-2.0. Read the licence text before commercial use: the name alone does not tell you what is allowed.
The configuration allows 524,288 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.
This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.
Also in the library
K2-Horizon-7B is a 9-billion-parameter decoder-only language model with a 524k token context window, released under Apache-2.0.
K2-Horizon-3.7B is a 3.7 billion-parameter dense decoder-only model with a 512 K token context, released openly by IFM.
K2-Horizon-32B-Stage1 is a 32-billion-parameter dense decoder-only model released by IFM for benchmarking agentic, coding and rea…
K2-Horizon-MoVA-36B-A4B is a sparse Mixture-of-Experts language model with MoVA attention, released by IFM.
Hosting
Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.