{"schema":"postcutoff/model@1","as_of":"2026-10-25T23:49:00+01:00","url":"https://postcutoff.com/m/k2-horizon-375b-a23b/","md":"https://postcutoff.com/m/k2-horizon-375b-a23b/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"k2-horizon-375b-a23b","name":"K2 Horizon 375B-A23B","org":"MBZUAI Institute of Foundation Models (IFM)","family":"K2 Horizon","released":"2026-09-03","status":"current","type":"reasoning-llm","modality_in":["text"],"modality_out":["text"],"open_weights":true,"model_license":"apache-2.0","context_window":524288,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Hugging Face (open weights, BF16)","model_id":"IFM/K2-Horizon-375B-A23B","url":"https://huggingface.co/IFM/K2-Horizon-375B-A23B"},{"provider":"Hugging Face (FP8)","model_id":"IFM/K2-Horizon-375B-A23B-FP8","url":"https://huggingface.co/IFM/K2-Horizon-375B-A23B-FP8"},{"provider":"Featherless","model_id":"IFM/K2-Horizon-375B-A23B","url":"https://featherless.ai/models/IFM/K2-Horizon-375B-A23B"},{"provider":"Vultr (GPU deployment guide)","docs":"https://docs.vultr.com/models/ifm-k2-horizon/k2-horizon-375b-a23b"}],"capabilities":[{"name":"Fully open frontier-scale MoE","detail":"375B total / 23B active sparse MoE released with weights, code (github.com/ifm-ai/xllm), pretraining and midtraining data (TxT360-v2) and W&B training logs, all Apache 2.0; MBZUAI calls K2 Horizon the largest fully open model release.","first":false,"discovered":"launch","source":"https://huggingface.co/IFM/K2-Horizon-375B-A23B"},{"name":"Native 512K context","detail":"524,288-token context native from midtraining onward.","first":false,"discovered":"launch","source":"https://huggingface.co/IFM/K2-Horizon-375B-A23B"},{"name":"Fastest model on Artificial Analysis (output speed, IFM API)","detail":"AA measured 507.4 output tokens/s on IFM's API, #1 of 78 in its comparison set, with Intelligence Index 31 (AA v4.3.2), the top non-Chinese open-weights score after Meta's Muse Spark Open per AA's Oct 16 post.","first":false,"discovered":"later","source":"https://artificialanalysis.ai/models/k2-horizon-375b-a23b"},{"name":"Agentic benchmarks with an audited coding score","detail":"Model card: Toolathlon Verified 65.3, BrowseComp 72.8, Terminal-Bench 2.1 70.2, GPQA Diamond 87.3, HLE (no tools) 32.0 (developer-reported; third-party coverage says an IFM reward-hacking audit lowered Terminal-Bench 2.1 to 66.9, not verified here).","first":false,"discovered":"launch","source":"https://huggingface.co/IFM/K2-Horizon-375B-A23B"}],"entry":null,"notes":"Maker: MBZUAI's Institute of Foundation Models (IFM, Abu Dhabi; successor of the LLM360 K2 line, W&B project llm360). Family of six models: 0.9B, 3.7B, 7B, 32B dense, 36B-A4B MoE and this 375B-A23B flagship (MBZUAI news, Sept 2026). Release date Sept 3, 2026 per Artificial Analysis FAQ and press (one listing says Sept 1). Reasoning model: set reasoning_effort via chat_template_kwargs, thinking in reasoning_content; vLLM (--reasoning-parser k2_horizon --tool-call-parser k2_horizon, TP 8 + expert parallel) and SGLang (8x H200). Artificial Analysis (read 2026-10-25, https://artificialanalysis.ai/models/k2-horizon-375b-a23b): Intelligence Index 31, output speed 507.4 tok/s (#1 of 78), TTFAT 6.05 s, single API provider (IFM) shown at $0.00/$0.00 — the price looks like a placeholder or free access, so no pricing block; IFM's hosted API endpoint and model id were not verified (ifm.ai returned 403). Featherless listing seen in search, not opened. Base model for Jais 3 (MBZUAI/Inception42, Oct 15, 2026). No timeline entry for the K2 Horizon launch itself yet.","verified":"2026-10-25","body_md":"The largest fully open (weights + data + code + logs) model family as of its release, from the UAE's MBZUAI. Fast on AA because IFM serves it at high throughput; intelligence is mid-tier.\n\nSources: [Hugging Face model card](https://huggingface.co/IFM/K2-Horizon-375B-A23B) ·\n[MBZUAI news](https://mbzuai.ac.ae/news/mbzuais-institute-of-foundation-models-launches-k2-horizon-the-worlds-largest-fully-open-ai-mo) ·\n[IFM blog](https://ifm.ai/blog/k2/) · [Artificial Analysis](https://artificialanalysis.ai/models/k2-horizon-375b-a23b) ·\n[Gulf Business](https://gulfbusiness.com/en/2026/artificial-intelligence/mbzuai-launches-k2-horizon-family-of-six-open-ai-models/)","page_url":"https://postcutoff.com/m/k2-horizon-375b-a23b/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":1056,"you_url":"https://postcutoff.com/you/k2-horizon-375b-a23b/","briefings":null}