When was K2 Horizon 7B released?

K2 Horizon 7B was released on September 3, 2026 by ifm. This is the official K2 Horizon 7B release date tracked on LLM Stats.

How big is K2 Horizon 7B?

K2 Horizon 7B has 7 billion parameters. It was trained on 22.9 trillion tokens. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created K2 Horizon 7B?

K2 Horizon 7B was created by ifm.

What is the license for K2 Horizon 7B?

K2 Horizon 7B is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Where is the K2 Horizon 7B paper or technical report?

K2 Horizon 7B has a paper or technical report available at https://ifm.ai/blog/k2/. Use that source for architecture, training, release and evaluation details.

What models should I compare K2 Horizon 7B against?

Common K2 Horizon 7B comparisons include K2 Horizon 7B vs LongCat-Flash-Thinking-2601, K2 Horizon 7B vs Claude 3.7 Sonnet, K2 Horizon 7B vs Grok 4 Fast. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.

K2 Horizon 7B Benchmarks, Pricing & Context Window

Name: K2 Horizon 7B
Author: ifm

K2 Horizon 7B: Benchmarks, Pricing & Context Window

K2 Horizon 7B is a language model from Institute of Foundation Models, released in September 2026.

K2 Horizon 7B is the medium dense member of IFM's (MBZUAI) fully open K2 Horizon family: a 7B-core decoder-only reasoning model (36 layers; about 9.0B parameters in the released safetensors including its 250K-token vocabulary embeddings)

K2 Horizon 7B benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for K2 Horizon 7B across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How K2 Horizon 7B holds up as conversations get longer.

Quality Tracker

K2 Horizon 7B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Fri Oct 30 2026

Notice missing or incorrect data?

K2 Horizon 7B model size

K2 Horizon 7B has 7 billion parameters and was trained on 22.9 trillion tokens. See how it compares to other models in the same parameter range.

ParametersTraining tokens

22.9Ttokens

3271× tokens-to-params ratio

Small (3–10B)

1B7B70B405B

Try now

huggle

K2 Horizon 7Bin Huggle

Make it with
K2 Horizon 7B.

K2 Horizon 7B latency

K2 Horizon 7B time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

K2 Horizon 7B examples

Recent arena outputs from K2 Horizon 7B, picked from the highest-ranked matchups.

K2 Horizon 7B license

K2 Horizon 7B is released under the Apache 2.0 license, which permits commercial use, has 7.0B parameters.

License: Apache 2.0; Commercial use allowed
Parameters: 7.0B

Apache License 2.0 - allows commercial use

K2 Horizon 7B resources

Official sources for K2 Horizon 7B: official launch post, source repository, model weights.

K2 Horizon 7B vs other models

The most-compared alternatives to K2 Horizon 7B are LongCat-Flash-Thinking-2601, Claude 3.7 Sonnet, Grok 4 Fast. Open any pair side-by-side for benchmarks, pricing, context, and latency.