K2-Horizon-32B-NVFP4

K2-Horizon-32B-Stage1-NVFP4

Pre-training Code - Post-training Code - Pretraining Data - Midtraining Data

[!NOTE] This repository contains an NVFP4-quantized version of IFM/K2-Horizon-32B.

All linear layers except lm_head are quantized to NVFP4:

• Weights: NVFP4
• Activations: NVFP4

The NVFP4 model shows slightly lower performance than the original BF16 model on our evaluations, while reducing memory footprint and enabling faster inference on NVFP4-capable hardware.

Serving note: Requires NVIDIA Blackwell-generation GPUs (B-series) or newer with native NVFP4 support.

K2-Horizon-32B-Stage1 is the large dense member of the K2-Horizon family: a 32B decoder-only model with a 512K context window. <span style="color:#d92d20;font-weight:600">Note: final checkpoint to be released.</span>

<p align="center"> <img src="assets/k2-horizon-32b-benchmarks.png" alt="K2-Horizon-32B-Stage1 benchmark results against open MoE, dense, and closed models" width="100%"> </p>

K2-Horizon-32B-Stage1 Highlights

• Strong dense baseline. A 32B dense model evaluated on the same agentic, coding, and reasoning benchmarks as the rest of the family (see Benchmark Results). Results are for stage 1 of the final model training; results for stage 2 will be out soon.
• 512K context. Native 524,288-token context from the midtraining stages onward.
• Intermediate checkpoints. Intermediate checkpoints will be released so capability changes can be studied across training rather than at a single checkpoint.
• Fully open. Training data/recipe and the training code will be made public.

Benchmark Results

<!-- TABLE:START --> <div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;margin:0 auto;padding:8px 0 16px;overflow-x:auto"><table style="display:table;width:100%;table-layout:fixed;border-collapse:collapse;font-size:12px;margin:0"><thead><tr><th style="width:30%;border-bottom:none"></th><th colspan="1" style="padding:6px 4px 2px;text-align:center;font-size:11px;font-weight:600;letter-spacing:0.04em;text-transform:uppercase;opacity:0.65;border-bottom:1px solid rgba(128,128,128,0.25)"></th><th colspan="3" style="padding:6px 4px 2px;text-align:center;font-size:11px;font-weight:600;letter-spacing:0.04em;text-transform:uppercase;opacity:0.65;border-bottom:1px solid rgba(128,128,128,0.25)">Open-weight dense models</th></tr><tr><th style="padding:10px 6px;text-align:left;border-bottom:2px solid #2450D6"></th><th style="padding:10px 3px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;color:#2450D6;font-size:12.5px;line-height:1.2;width:17.50%;overflow-wrap:anywhere;background:rgba(36,80,214,0.08);">K2-Horizon-32B-Stage1</th><th style="padding:10px 3px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;color:#2450D6;font-size:12.5px;line-height:1.2;width:17.50%;overflow-wrap:anywhere;">Qwen3.8-27B</th><th style="padding:10px 3px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;color:#2450D6;font-size:12.5px;line-height:1.2;width:17.50%;overflow-wrap:anywhere;">Muse Glimmer-30B</th><th style="padding:10px 3px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;color:#2450D6;font-size:12.5px;line-height:1.2;width:17.50%;overflow-wrap:anywhere;">IBM Granite 4.2 30B</th></tr></thead><tbody><tr><td style="padding:7px 4px 7px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;font-weight:600"># Params</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">32B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">27B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">30B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">30B</td></tr><tr><td style="padding:7px 4px 7px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;font-weight:600"># Activated params</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">32B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">27B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">30B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">30B</td></tr><tr><td style="padding:7px 4px 7px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;font-weight:600">Architecture</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">Dense</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">Dense</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">Dense</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">Dense</td></tr><tr><td colspan="5" style="padding:6px 10px;font-weight:600;font-size:12.5px;color:#2450D6;border-bottom:1px solid rgba(36,80,214,0.25);background:rgba(36,80,214,0.12)">Agents</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">tau3-Banking</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Agentic tool use</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">22.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>48.0</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">23.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">14.4</td></tr><tr><td colspan="5" style="padding:6px 10px;font-weight:600;font-size:12.5px;color:#2450D6;border-bottom:1px solid rgba(36,80,214,0.25);background:rgba(36,80,214,0.12)">Coding</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Terminal-Bench 2.1</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Agentic terminal use</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">36.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>79.8</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">51.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">26.6</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">SciCode</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Scientific coding</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">30.2</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>44.7</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">43.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">36.6</td></tr><tr><td colspan="5" style="padding:6px 10px;font-weight:600;font-size:12.5px;color:#2450D6;border-bottom:1px solid rgba(36,80,214,0.25);background:rgba(36,80,214,0.12)">Scientific Reasoning</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Humanity's Last Exam (without tools)</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Expert-level reasoning</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">22.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>33.9</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">22.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">11.2</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">GPQA Diamond</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Graduate-level science QA</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">82.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>90.5</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">83.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">64.4</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">CritPt</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Frontier physics reasoning</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">1.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>5.4</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">2.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">0.3</td></tr><tr><td colspan="5" style="padding:6px 10px;font-weight:600;font-size:12.5px;color:#2450D6;border-bottom:1px solid rgba(36,80,214,0.25);background:rgba(36,80,214,0.12)">General</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">AA-LCR</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Long-context reasoning</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">65.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">77.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>80.0</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">46.7</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">AA-Omniscience Accuracy</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Factual accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">16.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">15.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>27.0</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">10.1</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">AA-Omniscience Non-Hallucination</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Non-hallucination rate</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(36,80,214,0.08);">58.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">69.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">18.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>74.4</strong></td></tr></tbody></table></div> <!-- TABLE:END --> <p style="font-size:1.25em;line-height:1.6">Scores in %. Bold marks the best score in each row. Sections follow the <a href="https://artificialanalysis.ai/methodology/intelligence-benchmarking">Artificial Analysis Intelligence Index</a> categories. Baseline scores are from Artificial Analysis; Muse Glimmer-30B at high reasoning effort, other open models in their reasoning mode.</p>

NVFP4 vs. BF16

<!-- TABLE:START --> <div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;margin:0 auto;padding:8px 0 16px;overflow-x:auto"> <table style="display:table;width:100%;border-collapse:collapse;font-size:12px;margin:0;table-layout:fixed;"> <thead> <tr> <th style="width:16%;padding:10px 8px;text-align:left;font-weight:600;border-bottom:2px solid #2450D6;color:#2450D6;font-size:12.5px;"> K2-Horizon-32B-Stage1 </th> <th style="padding:10px 8px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;">IFEval (Prompt)</th> <th style="padding:10px 8px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;">GSM8K</th> <th style="padding:10px 8px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;">MBPP</th> <th style="padding:10px 8px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;">MMLU-Pro</th> <th style="padding:10px 8px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;">GPQA-Diamond</th> <th style="padding:10px 8px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;">BBH (3-shot)</th> <th style="padding:10px 8px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;">AIME 26 (avg @ 32)</th> <th style="padding:10px 8px;text-align:center;font-weight:600;border-bottom:2px solid #2450D6;">Average</th> </tr> </thead> <tbody> <!-- BF16 highlighted --> <tr style="background:rgba(36,80,214,0.12);"> <td style="padding:7px 8px;border-bottom:1px solid rgba(36,80,214,0.25);font-weight:700;color:#2450D6;"> BF16 </td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(36,80,214,0.25);">86.69</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(36,80,214,0.25);">96.21</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(36,80,214,0.25);">94.40</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(36,80,214,0.25);">81.52</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(36,80,214,0.25);">81.76</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(36,80,214,0.25);">93.20</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(36,80,214,0.25);">92.60</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(36,80,214,0.25);">89.5</td> </tr> <tr> <td style="padding:7px 8px;border-bottom:1px solid rgba(128,128,128,0.15);font-weight:600;">NVFP4</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);">85.40</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);">96.59</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);">93.20</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);">80.47</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);">78.82</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);">93.30</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);">91.15</td> <td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);">88.4</td> </tr> </tbody> </table> </div> <!-- TABLE:END --> The evaluation context length is set to 65,536 tokens. Unless otherwise specified, all tasks are evaluated in a 0-shot setting. The NVFP4 models have currently been evaluated only on non-agent tasks. Results for agent tasks will be released later.

Quickstart

Serving

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

vllm serve IFM/K2-Horizon-32B-NVFP4 \
  --revision main \
  --model-impl vllm \
  --tensor-parallel-size 2 \
  --trust-remote-code \
  --max-model-len 131072 \
  --reasoning-parser k2_horizon \
  --enable-auto-tool-choice \
  --tool-call-parser k2_horizon

SGLang, adapted from the BF16 recipe validated on 2× H200 in the SGLang K2 Horizon cookbook:

python3 -m sglang.launch_server \
  --model-path IFM/K2-Horizon-32B-NVFP4 \
  --revision main \
  --tp 2 \
  --attention-backend fa3 \
  --reasoning-parser k2_horizon \
  --tool-call-parser k2_horizon \
  --host 0.0.0.0 --port 30000

API Usage

[!Tip] Recommended settings: reasoning_effort="high", temperature=1.0, top_p=0.95. 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-32B-NVFP4",
    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-32B-NVFP4"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, device_map="auto", dtype="auto", 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))

Best Practices

1. Reasoning effort: always high. All reported results use high reasoning effort. Pass {"chat_template_kwargs": {"reasoning_effort": "high"}} on every request.
2. Sampling parameters. temperature=1.0, top_p=0.95.
3. Serving. Use the SGLang command above: TP=2, FlashAttention-3. Precision is read from the checkpoint, so no --dtype flag is needed. This checkpoint needs NVIDIA Blackwell GPUs with native NVFP4 support; the TP/EP settings come from the BF16 recipe and have not been re-validated here. Full recipes for every K2-Horizon size, with measured H200 latency and throughput, are in the SGLang cookbook and the vLLM recipe.
4. 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.

Citation

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