{"slug": "ornith-1-5-35b-a3b", "title": "Ornith-1.5-35B-A3B", "summary": "Ornith AI released Ornith-1.5-35B-A3B, a 36B-parameter mixture-of-experts model with 3B active parameters per token, on August 18, 2026, under an MIT license on HuggingFace. The model achieves 79.0 on SWE-bench Verified and 89.2 on GPQA-Diamond, outperforming dense models like Gemma 4-31B and Qwen 3.6-35B on agentic coding, with a 262K context window and local-friendly GGUF quantizations.", "body_md": "# Ornith-1.5-35B-A3B\n\nMoE enthusiast**~36B total, ~3B active per token (MoE)** - the local-favorite Ornith-1.5 size, released 2026-08-18. Activates only 3B parameters per token yet outperforms dense models like Gemma 4-31B and Qwen 3.6-35B on agentic coding. 262K context, MIT-licensed on HuggingFace at `ornith-ai/Ornith-1.5-35B-A3B`\n\n(GGUF, FP8, and NVFP4 quantizations).\n\n-\n**Coding (vendor self-reported):** Terminal-Bench 2.1 67.8, SWE-bench Verified 79.0, SWE-bench Pro 59.6, NL2Repo 46.2. -\n**Reasoning:** HLE 25.6 (no tools) / 33.4 (with tools), GPQA-Diamond 89.2. -\n**Agentic:** MCP-Atlas 70.2, Toolathlon-Verified 48.7, ClawEval 72.5.\n\n**Local-friendly.** Runs on enthusiast-class GPUs via GGUF quantizations; a strong open-weight pick for local agentic coding. Vendor benchmarks are claims pending independent replication.\n\n- 36.0B\n- 262k\n- mit\n- 🇺🇸 USA\n- Aug 2026\n\n## Scores\n\n## Run it locally\n\nPer-quant memory needs and a static \"can you run it?\" reference - no rig entry required\n\n### Can you run it? - reference rigs\n\n| Rig | Q4_K_M | Q5_K_M | Q6_K | Q8_0 | BF16 |\n|---|---|---|---|---|---|\n| NVIDIA Jetson Orin NX 16GB |\n|\n\n[no -> cloud](#cloud-pricing)[no -> cloud](#cloud-pricing)[no -> cloud](#cloud-pricing)[no -> cloud](#cloud-pricing)[no -> cloud](#cloud-pricing)[no -> cloud](#cloud-pricing)[no -> cloud](#cloud-pricing)[no -> cloud](#cloud-pricing)[no -> cloud](#cloud-pricing)[no -> cloud](#cloud-pricing)[no -> cloud](#cloud-pricing)Fit tiers use the same will-it-run logic as the rig finder. For comfortable fits, the badge reflects decode speed: fast >=20 t/s, ok 8-20 t/s, slow <8 t/s. t/s is a bandwidth estimate, not a measured benchmark.\n\n## Download options\n\n## Or run it in the cloud\n\nNo per-token API provider pricing tracked for Ornith-1.5-35B-A3B yet.\nFor flagship list prices, see the\n[calculator](/calculator).\n\n## Inference cost over time\n\nData accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.", "url": "https://wpnews.pro/news/ornith-1-5-35b-a3b", "canonical_source": "https://tokenstead.ai/models/ornith-1-5-35b-a3b", "published_at": "2026-08-24 20:51:38+00:00", "updated_at": "2026-08-24 21:15:47.413201+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-research"], "entities": ["Ornith AI", "Ornith-1.5-35B-A3B", "HuggingFace", "Gemma 4-31B", "Qwen 3.6-35B"], "alternates": {"html": "https://wpnews.pro/news/ornith-1-5-35b-a3b", "markdown": "https://wpnews.pro/news/ornith-1-5-35b-a3b.md", "text": "https://wpnews.pro/news/ornith-1-5-35b-a3b.txt", "jsonld": "https://wpnews.pro/news/ornith-1-5-35b-a3b.jsonld"}}