{"slug": "ornith-1-5-9b", "title": "Ornith-1.5-9B", "summary": "Ornith AI released Ornith-1.5-9B, a 9-billion-parameter dense language model, on August 18, 2026, claiming it matches or exceeds larger models like Gemma 4-31B and Qwen 3.6-35B on agentic coding tasks. The model, available under an MIT license on HuggingFace, scores 70.6 on SWE-bench Verified and 86.4 on GPQA-Diamond, with a 262K context window and quantized builds for edge devices.", "body_md": "# Ornith-1.5-9B\n\nconsumer**~9B Dense** - the edge-deployable Ornith-1.5, released 2026-08-18. Compact enough for phones (a quantized Ornith-1.5-9B-Mobile variant targets iOS/Android) yet matches or exceeds much larger models like Gemma 4-31B and Qwen 3.6-35B on agentic coding. 262K context, MIT-licensed on HuggingFace at `ornith-ai/Ornith-1.5-9B`\n\n(GGUF and MLX quantizations).\n\n-\n**Coding (vendor self-reported):** Terminal-Bench 2.1 46.2, SWE-bench Verified 70.6, SWE-bench Pro 47.5, NL2Repo 32.4. -\n**Reasoning:** HLE 20.2 (no tools) / 30.5 (with tools), GPQA-Diamond 86.4. -\n**Agentic:** MCP-Atlas 54.2, Toolathlon-Verified 41.2, ClawEval 66.5.\n\n**Runs almost anywhere.** Quantized builds run on phones, laptops, and small GPUs; the strongest open-weight coding model at this size. Vendor benchmarks are claims pending independent replication.\n\n- 9.0B\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| 4x H100 80GB (320GB) | fast 1274.7t/s | fast 1109.6t/s | fast 974.6t/s | fast 752.7t/s | fast 400.5t/s |\n| NVIDIA DGX Station 748GB | fast 761.0t/s | fast 662.5t/s | fast 581.9t/s | fast 449.4t/s | fast 239.1t/s |\n| 4x RTX 5090 (128GB) | fast 681.8t/s | fast 593.6t/s | fast 521.3t/s | fast 402.6t/s | fast 214.2t/s |\n| 4x RTX 4090 (96GB) | fast 383.5t/s | fast 333.9t/s | fast 293.3t/s | fast 226.5t/s | fast 120.5t/s |\n| 2x RTX 5090 (64GB) | fast 340.9t/s | fast 296.8t/s | fast 260.7t/s | fast 201.3t/s | fast 107.1t/s |\n| 2x RTX 3090 (48GB) | fast 178.1t/s | fast 155.1t/s | fast 136.2t/s | fast 105.2t/s | fast 56.0t/s |\n| Single RTX 5090 (32GB) | fast 170.5t/s | fast 148.4t/s | fast 130.3t/s | fast 100.7t/s | fast 53.6t/s |\n| Mac Studio M4 Ultra 192GB | fast 113.3t/s | fast 98.6t/s | fast 86.6t/s | fast 66.9t/s | fast 35.6t/s |\n| Mac Studio M4 Ultra 512GB | fast 113.3t/s | fast 98.6t/s | fast 86.6t/s | fast 66.9t/s | fast 35.6t/s |\n| Single RTX 4090 (24GB) | fast 95.9t/s | fast 83.5t/s | fast 73.3t/s | fast 56.6t/s | fast 30.1t/s |\n| MacBook Pro M5 Max 128GB | fast 63.7t/s | fast 55.5t/s | fast 48.7t/s | fast 37.6t/s | fast 20.0t/s |\n| Single GTX 1080 Ti (11GB) | fast 46.0t/s | fast 40.1t/s | fast 35.2t/s | tight |\n|\n\n[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-1.5-9B 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-1-5-9b", "canonical_source": "https://tokenstead.ai/models/ornith-1-5-9b", "published_at": "2026-08-24 20:51:38+00:00", "updated_at": "2026-08-24 21:15:51.261229+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-research"], "entities": ["Ornith AI", "Ornith-1.5-9B", "HuggingFace", "Gemma 4-31B", "Qwen 3.6-35B"], "alternates": {"html": "https://wpnews.pro/news/ornith-1-5-9b", "markdown": "https://wpnews.pro/news/ornith-1-5-9b.md", "text": "https://wpnews.pro/news/ornith-1-5-9b.txt", "jsonld": "https://wpnews.pro/news/ornith-1-5-9b.jsonld"}}