3
followers ·
23 following Building the AI-native stack. Agents as infrastructure, safety as architecture, performance as plumbing. I publish the receipts: papers, datasets, demos.
replied to satgeze 'spost about 1 hour ago https://huggingface.co/satgeze/Ornith-1.0-35B-1M-GGUF
Ornith-1.0 with a 1,048,576-token context window, tested instead of claimed 🦜
Ornith is Qwen3.5-family under the hood, so YaRN factor 4 extends it from 262K native to exactly 1M. I baked that into the GGUF metadata (no fine-tuning, weights bit-identical) so llama.cpp and Ollama apply it with zero flags, then ran full needle-in-a-haystack ladders on my own hardware:
- satgeze/Ornith-1.0-35B-1M-GGUF: 10/10 needles at every rung from 32K through 1M, replicated with fresh seeds (M3 Max 128GB, ~6.8h cold 1M prefill)
- satgeze/Ornith-1.0-9B-1M-GGUF: perfect through 524K, honest 7/10 at 1M under Q4 + q8_0 KV, failure band charted in the card
- satgeze/Ornith-1.0-397B-1M-GGUF: IQ1_M through Q4_K_M as split GGUFs, coherence-gated
Also in the repos:
- Vision: Ornith kept the Qwen3.5 multimodal skeleton, so the VL vision tower (extracted by bartowski) attaches at runtime via llama-server --mmproj. OCR-tested on the 9B and 35B, mmproj files bundled.
- A measured residency matrix: on a single RTX 5090, every 9B quant up to Q6_K holds the full 1M window at 100 percent GPU, 162 to 244 tok/s.
- Quality gates: every low-bit quant passed a coherence test before upload. The 35B IQ1_S failed and was deleted rather than shipped.
Harness, method writeup, and raw per-needle data: https://github.com/satindergrewal/ornith-1m
All MIT. Credit to DeepReinforce for the models and bartowski for the imatrix quants and vision towers. If a config breaks retrieval for you, tell me and it goes in the card.
reacted to satgeze 'spost with 🤗 about 1 hour ago https://huggingface.co/satgeze/Ornith-1.0-35B-1M-GGUF
Ornith-1.0 with a 1,048,576-token context window, tested instead of claimed 🦜
Ornith is Qwen3.5-family under the hood, so YaRN factor 4 extends it from 262K native to exactly 1M. I baked that into the GGUF metadata (no fine-tuning, weights bit-identical) so llama.cpp and Ollama apply it with zero flags, then ran full needle-in-a-haystack ladders on my own hardware:
- satgeze/Ornith-1.0-35B-1M-GGUF: 10/10 needles at every rung from 32K through 1M, replicated with fresh seeds (M3 Max 128GB, ~6.8h cold 1M prefill)
- satgeze/Ornith-1.0-9B-1M-GGUF: perfect through 524K, honest 7/10 at 1M under Q4 + q8_0 KV, failure band charted in the card
- satgeze/Ornith-1.0-397B-1M-GGUF: IQ1_M through Q4_K_M as split GGUFs, coherence-gated
Also in the repos:
- Vision: Ornith kept the Qwen3.5 multimodal skeleton, so the VL vision tower (extracted by bartowski) attaches at runtime via llama-server --mmproj. OCR-tested on the 9B and 35B, mmproj files bundled.
- A measured residency matrix: on a single RTX 5090, every 9B quant up to Q6_K holds the full 1M window at 100 percent GPU, 162 to 244 tok/s.
- Quality gates: every low-bit quant passed a coherence test before upload. The 35B IQ1_S failed and was deleted rather than shipped.
Harness, method writeup, and raw per-needle data: https://github.com/satindergrewal/ornith-1m
All MIT. Credit to DeepReinforce for the models and bartowski for the imatrix quants and vision towers. If a config breaks retrieval for you, tell me and it goes in the card.
View all activity 
