K2-Horizon-7B

K2-Horizon-7B is the medium dense member of the K2-Horizon family: a 7B-core decoder-only model with a 512K context window.

K2-Horizon-7B Highlights

• Strong dense baseline. A 7B-class dense model evaluated across agentic, coding, long-context, and reasoning benchmarks.
• 512K context. Native 524,288-token context from the midtraining stages onward.
• Diffusion Adapters. For faster inference (HF).
• Intermediate checkpoints. Intermediate checkpoints are released so capability changes can be studied across training rather than at a single checkpoint.
• Fully open. Training data and recipe, training code, and evaluation resources are public.

Benchmark Results

The chart at the top of this card shows K2-Horizon-7B against selected reference models. The table below lists every comparison model used in the figure.

Full Results

		Reference models · weak to strong
Benchmark	K2-Horizon-7B	Reference 1	Reference 2	Reference 3
Math
HMMT Feb 2026 Competition mathematics	73.3	Gemma 4-12B 63.1	Qwen3.5-9B 65.7	Granite 4.2-8B 66.5
Coding
SWE-bench Verified Software engineering	70.6	Gemma 4-12B 30.6	Granite 4.2-8B 47.7	Qwen3.5-9B 50.8
Scientific Reasoning
HLE Expert-level reasoning	18.6	Granite 4.2-8B 9.7	Qwen3.5-9B 14.9	Gemma 4-12B 15.7
Coding
SciCode Scientific coding	31.6	Qwen3.5-9B 27.5	Mistral Small 4 28.0	Granite 4.2-8B 30.4
General
LCR Long-context reasoning	68.0	Granite 4.2-8B 43.3	Gemma 4-12B 61.7	Qwen3.5-9B 65.3
Coding
Terminal-Bench 2.1 Agentic terminal use	39.1	Granite 4.2-8B 18.4	Gemma 4-12B 27.3	Qwen3.5-9B 29.2
Agents
tau3-Banking Agentic tool use	25.8	Qwen3.5-9B 7.0	Granite 4.2-8B 7.6	Muse Glimmer-30B 24.0
BrowseComp Web browsing	59.0	DeepSeek V4 Flash-0423 53.5	GPT-5 54.9	LongCat Flash Thinking-2601 56.6

Scores in %. Bold marks the best score in each row. BrowseComp: our model uses the Discard-all@95k context-length protocol proposed in the DeepSeek-V3.2 technical report; comparison models may use different harnesses.

Quickstart

Serving

vLLM, recipe at recipes.vllm.ai/IFM:

vllm serve IFM/K2-Horizon-7B \
  --trust-remote-code \
  --dtype bfloat16 \
  --tensor-parallel-size 1 \
  --reasoning-parser k2_horizon \
  --enable-auto-tool-choice \
  --tool-call-parser k2_horizon

Use an exact branch name from the inventory with vLLM's --revision option. For example, --revision pretrain_1100000 selects the final checkpoint of Pretraining, at step 1,100,000.

SGLang, this is the recipe validated in the SGLang K2 Horizon cookbook:

sglang serve \
  --model-path IFM/K2-Horizon-7B \
  --revision 69ada542b68fe13d767479db2ab9421baff88681 \
  --tp 1 \
  --dtype bfloat16 \
  --attention-backend fa3 \
  --reasoning-parser k2_horizon \
  --host 0.0.0.0 \
  --port 30000

API Usage

Recommended settings: reasoning_effort="high", temperature=1.0, top_p=0.95, and at least 32,768 output tokens. Reasoning depth is selected per request through chat_template_kwargs. Thinking is returned in reasoning_content and the answer in content.

from openai import OpenAI

client = OpenAI(base_url="http://localhost:30000/v1", api_key="EMPTY")
response = client.chat.completions.create(
    model="IFM/K2-Horizon-7B",
    messages=[{"role": "user", "content": "Explain the result step by step."}],
    temperature=1.0,
    top_p=0.95,
    max_tokens=32768,
    extra_body={"chat_template_kwargs": {"reasoning_effort": "high", "tool_call_format": "xml"}},
)
message = response.choices[0].message
print("Reasoning:", getattr(message, "reasoning_content", None))
print("Answer:", message.content)

Our model supports multiple tool calls formats, which can be changed with chat_template_kwargs. The supported values are json, xml, and xml_typed . The default is xml. Keep --tool-call-parser k2_horizon enabled to parse the selected format.

Transformers

Validated with Transformers 5.15.0, PyTorch 2.13.0, Safetensors 0.8.0.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "IFM/K2-Horizon-7B"
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))

Training Overview

The table below lists the training stages in order and the purpose of each stage.

Training steps are counted within each stage or phase. Token budgets cover only the additional training in that stage or phase. For example, the 50B tokens listed for SFT Phase 2 are additional to the 219B tokens in Phase 1, bringing the cumulative budget to 269B tokens by the end of Phase 2. Here, B and T denote billion and trillion tokens, respectively.

Each stage or phase continues from the final checkpoint of the preceding stage or phase.

Some stages, such as SFT, have multiple phases with slight changes to the data mix while retaining the same overall purpose. During RL, training branches into five expert models, which are then merged, as described below.

Training stage	Training steps	Training tokens	Sequence length	Purpose
Pretraining	1100000	22.9T	8K	Pretraining.
Midtraining — Stage 1	55000	1.1T	32K	Context extension.
Midtraining — Stage 2	25000	498B	128K	Context extension.
Midtraining — Stage 3	5500	110B	512K	Context extension.
Midtraining — Stage 4	10000	199B	512K	Continued context extension from Stage 3, with the data mix shifted toward agentic and reasoning SFT data.
RL	To be updated	To be updated	512K	We trained five expert models from the final checkpoint of Midtraining Stage 4: math, code1, code2, search, and tool use. We then merged the expert models.
SFT — Phase 1	10000	199B	512K	SFT for better domain coverage, starting from the merged RL checkpoint.
SFT — Phase 2	2500	50B	512K	SFT on a high-quality subset of the data used in Phase 1, with learning rate decay.

Release Artifacts

The tables below list the release artifacts for K2-Horizon-7B, their availability, and the expected release dates for remaining items.

Last updated: 2026-09-11

Status:

• Available — fully released for the scope listed;
• Partial — some items are available, with remaining items listed in the notes;
• In Progress — being prepared for release but not yet available.

Artifact Index

Artifact	Link	Status	Remaining items / expected availability
Model card	Hugging Face	Available	N/A
Training logs	W&B	Available	N/A
Blog post	Blog post	Available	N/A
Checkpoints	Checkpoint inventory	Partial	See details below
Technical report	Not yet available	In Progress	End of September 2026
Code repository	GitHub	In Progress	End of September 2026

Checkpoint Inventory

Model repository: IFM/K2-Horizon-7B

Branch names below refer to this repository. Patterns containing * group branches by training stage or phase. The * is a placeholder for a training-step number, not a literal branch name. Intermediate checkpoint groups exclude the final checkpoint listed separately; a pattern does not imply that a checkpoint is available at every step.

For example, sft_1_11000 is the checkpoint saved at training step 11,000 within SFT Phase 1, and is the final checkpoint of that phase. The numeric suffix is the step within the named stage or phase, not the cumulative step across all training. Thus, sft_2_2500 refers to step 2,500 within SFT Phase 2.

For a partially released group, the available checkpoints and the remaining checkpoints are listed in the notes.

Checkpoint	Branch / repository	Status	Remaining items / expected availability
Pretrain Intermediate Checkpoints	pretrain_*	Available	N/A
Pretrain Final Checkpoint	pretrain_1100000	Available	N/A
Midtrain Stage 1 Intermediate Checkpoints	mid_1_*	Available	N/A
Midtrain Stage 1 Final Checkpoint	mid_1_55000	Available	N/A
Midtrain Stage 2 Intermediate Checkpoints	mid_2_*	Available	N/A
Midtrain Stage 2 Final Checkpoint	mid_2_25000	Available	N/A
Midtrain Stage 3 Intermediate Checkpoints	mid_3_*	Available	N/A
Midtrain Stage 3 Final Checkpoint	mid_3_5500	Available	N/A
Midtrain Stage 4 Intermediate Checkpoints	mid_4_*	Available	N/A
Midtrain Stage 4 Final Checkpoint	mid_4_10000	Available	N/A
RL Math Expert Checkpoint	rl_math	In Progress	Mid-September 2026
RL Code1 Expert Checkpoint	rl_code1	In Progress	Mid-September 2026
RL Code2 Expert Checkpoint	rl_code2	In Progress	Mid-September 2026
RL Search Expert Checkpoint	rl_search	In Progress	Mid-September 2026
RL Tool Use Expert Checkpoint	rl_tool_use	In Progress	Mid-September 2026
RL Merged Final Checkpoint	rl_merged	Available	N/A
SFT Phase 1 Intermediate Checkpoints	sft_1_*	Available	N/A
SFT Phase 1 Final Checkpoint	sft_1_11000	Available	N/A
SFT Phase 2 Intermediate Checkpoints	sft_2_*	Available	N/A
SFT Phase 2 Final Checkpoint	sft_2_2500	Available	N/A

Best Practices

1. Reasoning effort: always high. All reported results use high reasoning effort. Pass {"chat_template_kwargs": {"reasoning_effort": "high"}} on every request; medium and low trade accuracy for speed and are not recommended for evaluation.
2. Sampling parameters. temperature=1.0, top_p=0.95.
3. Output length. Allow at least 32,768 output tokens so reasoning is never cut off. Truncated reasoning is a failed response, not a shorter one.
4. Serving. Use the validated SGLang recipe above: BF16, TP=1, FlashAttention-3. Full recipes for every K2-Horizon size, with measured H200 latency and throughput, are in the SGLang cookbook.
5. Parsers. Enable the k2_horizon reasoning parser for chat, and add the k2_horizon tool-call parser for agent use. Leave both off for plain completion-style generation.
6. Revisions. Pin a revision tag when reproducibility matters. main is the default checkpoint; base_final and the mid_*_final tags identify training stages.

Citation

@misc{k2horizon2026,
  title  = {Introducing K2 Horizon: Frontier Performance, Radically Open},
  author = {{IFM Team}},
  year   = {2026},
  url    = {https://ifm.ai/blog/k2/},
}