Model library / IFM
K2-Horizon-7B is a 9-billion-parameter decoder-only language model with a 524k token context window, released under Apache-2.0.
Parameters in total
Context length in tokens, as published
Weights at the released precision
Licence declared on the repository
Overview
K2-Horizon-7B is a decoder-only language model released by IFM. The publisher describes it as a medium-density member of the K2-Horizon family, built on a 7-billion-core architecture and evaluated on agentic, coding, long-context and reasoning benchmarks. It targets a range of general-purpose AI tasks requiring strong baseline performance.
In practice the model contains roughly nine billion parameters and stores weights in bfloat16 format. It supports a native context window of 524,288 tokens, enabling processing of very long inputs. The Apache-2.0 licence permits unrestricted commercial use. Deployment therefore requires hardware capable of handling a 9B-parameter model with large context memory, but benefits from the efficient weight representation.
Specification
| Repository | IFM/K2-Horizon-7B |
| Publisher | IFM |
| Published | 2 September 2026 |
| Architecture | K2HorizonForCausalLM |
| Model type | k2_horizon |
| Parameters | 8,999,178,240 |
| Layers | 36 |
| Hidden size | 4,096 |
| Attention heads | 32, 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 | 16.8 GiB | Full precision as released |
| fp8 | 8.4 GiB | 8-bit, near-lossless on most models |
| int4 | 4.2 GiB | 4-bit, smallest footprint |
The cache costs 144 KiB per token at 16-bit, so the full 524,288-token context of one request needs about 72.0 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 | 1 | 2.3 GiB | about 17,022 tokens |
| RTX 5090 32GB | 1 | 9.5 GiB | about 69,451 tokens |
| L40S 48GB | 1 | 23.9 GiB | about 174,309 tokens |
| A100 80GB | 1 | 52.7 GiB | about 384,024 tokens |
| H100 80GB | 1 | 52.7 GiB | about 384,024 tokens |
| RTX PRO 6000 96GB | 1 | 67.1 GiB | about 488,881 tokens |
| H200 141GB | 1 | 107.6 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-7B \ --max-model-len 16384 \ --gpu-memory-utilization 0.90
Questions
The weights take about 17 GiB at the released precision. That fits on one RTX 4090 24GB, which leaves roughly 2 GiB for the key-value cache.
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-375B-A23B is an open-weight sparse MiE language model from IFM with 379 B parameters, 23 B active per token and a 512 …
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.