| --- |
| pipeline_tag: text-generation |
| library_name: transformers |
| model_name: K2-Horizon-32B-Stage1 |
| language: |
| - en |
| license: apache-2.0 |
| datasets: |
| - IFM/K2-Horizon-Pretrain-Data |
| - IFM/K2-Horizon-Midtrain-Data |
| tags: |
| - k2-horizon |
| - 32b |
| - dense |
| - open-weights |
| - ifm |
| --- |
| |
| # K2-Horizon-32B-Stage1 |
|
|
| 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](#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> |
|
|
| ## Quickstart |
|
|
| ### Serving |
|
|
| vLLM, recipe at [recipes.vllm.ai/IFM](https://recipes.vllm.ai/IFM): |
|
|
| ```shell |
| vllm serve IFM/K2-Horizon-32B \ |
| --revision main \ |
| --model-impl vllm \ |
| --tensor-parallel-size 2 \ |
| --trust-remote-code \ |
| --dtype bfloat16 \ |
| --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 recipe validated on 2× H200 in the [SGLang K2 Horizon cookbook](https://docs.sglang.io/cookbook/autoregressive/IFM/K2-Horizon): |
|
|
| ```shell |
| python3 -m sglang.launch_server \ |
| --model-path IFM/K2-Horizon-32B \ |
| --revision main \ |
| --tp 2 \ |
| --dtype bfloat16 \ |
| --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`. |
| |
| ```python |
| 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", |
| 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. |
|
|
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| |
| model_id = "IFM/K2-Horizon-32B" |
| 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. |
|
|
| | 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. | |
| | SFT — Phase 1 | 11000 | 219B | 512K | SFT for better domain coverage, starting from the final checkpoint of midtraining stage 4. | |
| | 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-32B**, 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](https://huggingface.co/IFM/K2-Horizon-32B) | Available | N/A | |
| | Training logs | [W&B](https://wandb.ai/llm360/K2-Horizon-32B) | Available | N/A | |
| | Blog post | [Blog post](https://ifm.ai/blog/k2/) | Available | N/A | |
| | Checkpoints | [Checkpoint inventory](#checkpoint-inventory) | Available | See details below | |
| | Technical report | Not yet available | In Progress | End of September 2026 | |
| | Code repository | [GitHub](https://github.com/ifm-ai/xllm) | In Progress | End of September 2026 | |
|
|
| ### Checkpoint Inventory |
|
|
| **Model repository:** [IFM/K2-Horizon-32B](https://huggingface.co/IFM/K2-Horizon-32B) |
|
|
| 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 | |
| | 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. |
| 2. **Sampling parameters.** `temperature=1.0`, `top_p=0.95`. |
| 3. **Serving.** Use the validated SGLang recipe above: BF16, TP=2, FlashAttention-3. Full recipes for every K2-Horizon size, with measured H200 latency and throughput, are in the [SGLang cookbook](https://docs.sglang.io/cookbook/autoregressive/IFM/K2-Horizon) and the [vLLM recipe](https://recipes.vllm.ai/IFM). |
| 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 |
|
|
| ```bibtex |
| @misc{k2horizon2026, |
| title = {Introducing K2 Horizon: Frontier Performance, Radically Open}, |
| author = {{IFM Team}}, |
| year = {2026}, |
| url = {https://ifm.ai/blog/k2/}, |
| } |
| ``` |
