When was K2 Horizon 0.9B released?

K2 Horizon 0.9B was released on September 3, 2026 by ifm. This is the official K2 Horizon 0.9B release date tracked on LLM Stats.

How big is K2 Horizon 0.9B?

K2 Horizon 0.9B has 900 million parameters. It was trained on 5.0 trillion tokens. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created K2 Horizon 0.9B?

K2 Horizon 0.9B was created by ifm.

What is the license for K2 Horizon 0.9B?

K2 Horizon 0.9B 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 0.9B paper or technical report?

K2 Horizon 0.9B 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 0.9B against?

Common K2 Horizon 0.9B comparisons include K2 Horizon 0.9B vs Phi 4 Mini, K2 Horizon 0.9B vs Qwen3 VL 8B Instruct, K2 Horizon 0.9B vs Kimi K2 Base. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.

K2 Horizon 0.9B Benchmarks, Pricing & Context Window

Name: K2 Horizon 0.9B
Author: ifm

K2 Horizon 0.9B: Benchmarks, Pricing & Context Window

K2 Horizon 0.9B is a language model from Institute of Foundation Models, released in September 2026.

K2 Horizon 0.9B is the compact dense member of IFM's (MBZUAI) fully open K2 Horizon family: a 0.9B-class decoder-only reasoning model (28 layers, smaller 64K vocabulary; about 1.08B parameters in the released safetensors) pretrained on 5T

K2 Horizon 0.9B benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for K2 Horizon 0.9B across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How K2 Horizon 0.9B holds up as conversations get longer.

Quality Tracker

K2 Horizon 0.9B 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 0.9B model size

K2 Horizon 0.9B has 900 million parameters and was trained on 5 trillion tokens. See how it compares to other models in the same parameter range.

ParametersTraining tokens

900M

5Ttokens

5556× tokens-to-params ratio

Small (<3B)

900M

1B7B70B405B

Try now

huggle

K2 Horizon 0.9Bin Huggle

Make it with
K2 Horizon 0.9B.

K2 Horizon 0.9B latency

K2 Horizon 0.9B time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

K2 Horizon 0.9B examples

Recent arena outputs from K2 Horizon 0.9B, picked from the highest-ranked matchups.

K2 Horizon 0.9B license

K2 Horizon 0.9B is released under the Apache 2.0 license, which permits commercial use, has 900M parameters.

License: Apache 2.0; Commercial use allowed
Parameters: 900M

Apache License 2.0 - allows commercial use

K2 Horizon 0.9B resources

Official sources for K2 Horizon 0.9B: official launch post, source repository, model weights.

K2 Horizon 0.9B vs other models

The most-compared alternatives to K2 Horizon 0.9B are Phi 4 Mini, Qwen3 VL 8B Instruct, Kimi K2 Base. Open any pair side-by-side for benchmarks, pricing, context, and latency.