--- title: Ornith-1.0-397B-1M-GGUF canonical_url: "https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF" md_url: "https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF.md" repository: satgeze/Ornith-1.0-397B-1M-GGUF last_updated: 2026-07-06 license: mit pipeline_tag: text-generation tasks: - text-generation base_model: - deepreinforce-ai/Ornith-1.0-397B-FP8 base_model_relation: quantized library_name: - gguf downloads: 1495 stars: 0 tags: - gguf - long-context - yarn - ornith - llama.cpp - ollama --- # Ornith-1.0-397B-1M-GGUF > Ornith-1.0-397B-1M-GGUF - An open-source model by satgeze on ModelScope. Ornith-1.0-397B: 1M Context GGUF (YaRN) satgeze/Ornith-1.0-397B-1M-GGUF is a text-generation model on ModelScope. licensed under mit. derived from deepreinforce-ai/Ornith-1.0-397B-FP8. - **Repository**: satgeze/Ornith-1.0-397B-1M-GGUF - **License**: mit - **Tasks**: text-generation - **Base model**: deepreinforce-ai/Ornith-1.0-397B-FP8 - **Tags**: gguf, long-context, yarn, ornith, llama.cpp, ollama - **Downloads**: 1495 - **Stars**: 0 - **Last updated**: 2026-07-06 Source: https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF ---
Ornith # Ornith-1.0-397B: 1M Context GGUF (YaRN) [![GitHub](https://img.shields.io/badge/GitHub-aviary--1m%20(harness%20%2B%20method)-181717?logo=github)](https://github.com/satindergrewal/aviary-1m) [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT) [![Base](https://img.shields.io/badge/base-deepreinforce--ai%2FOrnith--1.0--397B-8A2BE2)](https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B) [![Context: 1M](https://img.shields.io/badge/context-1%2C048%2C576%20tokens-8A2BE2)]()
# All GGUF files live on ModelScope **Download here: [modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF)** This Hugging Face repo is a pointer page. The 397B quants are large (426 GB across IQ1_M, IQ2_M, and Q4_K_M splits), and the full set is hosted and verified on the ModelScope mirror to keep this account inside storage limits. Nothing was discontinued; the files are simply one click away. ## Every file, every mirror Nothing was discontinued: every quant is one click away. Hugging Face carries the curated picks, ModelScope always carries everything, and Ollama serves ready-to-run tags. | File | Size | Hugging Face | ModelScope | Ollama | |---|---|---|---|---| | `ornith-1.0-397b-1M-IQ1_M-00001-of-00003.gguf` | 39.8 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-IQ1_M-00001-of-00003.gguf) | - | | `ornith-1.0-397b-1M-IQ1_M-00002-of-00003.gguf` | 39.5 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-IQ1_M-00002-of-00003.gguf) | - | | `ornith-1.0-397b-1M-IQ1_M-00003-of-00003.gguf` | 12.1 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-IQ1_M-00003-of-00003.gguf) | - | | `ornith-1.0-397b-1M-IQ2_M-00001-of-00004.gguf` | 39.3 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-IQ2_M-00001-of-00004.gguf) | - | | `ornith-1.0-397b-1M-IQ2_M-00002-of-00004.gguf` | 40.0 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-IQ2_M-00002-of-00004.gguf) | - | | `ornith-1.0-397b-1M-IQ2_M-00003-of-00004.gguf` | 39.6 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-IQ2_M-00003-of-00004.gguf) | - | | `ornith-1.0-397b-1M-IQ2_M-00004-of-00004.gguf` | 14.3 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-IQ2_M-00004-of-00004.gguf) | - | | `ornith-1.0-397b-1M-Q4_K_M-00001-of-00007.gguf` | 39.0 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-Q4_K_M-00001-of-00007.gguf) | - | | `ornith-1.0-397b-1M-Q4_K_M-00002-of-00007.gguf` | 39.5 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-Q4_K_M-00002-of-00007.gguf) | - | | `ornith-1.0-397b-1M-Q4_K_M-00003-of-00007.gguf` | 38.9 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-Q4_K_M-00003-of-00007.gguf) | - | | `ornith-1.0-397b-1M-Q4_K_M-00004-of-00007.gguf` | 39.0 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-Q4_K_M-00004-of-00007.gguf) | - | | `ornith-1.0-397b-1M-Q4_K_M-00005-of-00007.gguf` | 39.4 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-Q4_K_M-00005-of-00007.gguf) | - | | `ornith-1.0-397b-1M-Q4_K_M-00006-of-00007.gguf` | 39.3 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-Q4_K_M-00006-of-00007.gguf) | - | | `ornith-1.0-397b-1M-Q4_K_M-00007-of-00007.gguf` | 6.8 GB | on ModelScope | [download](https://www.modelscope.ai/models/satgeze/Ornith-1.0-397B-1M-GGUF/resolve/master/ornith-1.0-397b-1M-Q4_K_M-00007-of-00007.gguf) | - | ## What the ModelScope repo contains [DeepReinforce's Ornith-1.0-397B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B) (397B MoE, Qwen3.5 family) with YaRN RoPE scaling baked into GGUF metadata for a 1,048,576-token context window, 4x the native 262,144. Weights bit-identical to the original; only rope metadata differs. | Quant | Size | Runs on | |---|---|---| | IQ1_M (3 split files) | 91 GB | 128 GB Mac (tested: it runs) | | IQ2_M (4 split files) | 132 GB | 192 GB+ unified or multi-GPU | | Q4_K_M (7 split files) | 241 GB | Server class, 256 GB+ | Needle certification for this size class is pending a GPU-pod session; the 9B and 35B repos carry fully certified ladders of the same recipe. MTP note: the official 397B checkpoint includes an MTP layer (config `mtp_num_hidden_layers: 1`) that GGUF conversions dropped; restoring it by extraction is on the roadmap. ## Run it ```bash llama-server -m ornith-1.0-397b-1M-IQ1_M-00001-of-00003.gguf -c 262144 -np 1 --jinja ``` llama.cpp loads split GGUFs automatically from the first part. Start at 262K and raise context per available memory; KV runs about 30 KB per token (15 of 60 layers full attention). ## Credits Ornith-1.0: [DeepReinforce](https://huggingface.co/deepreinforce-ai) (MIT), post-trained on Qwen 3.5. 1M YaRN extension: [SatGeze](https://huggingface.co/satgeze). Method and harness: [github.com/satindergrewal/aviary-1m](https://github.com/satindergrewal/aviary-1m). Sister repos with full ladders and MTP: [9B](https://huggingface.co/satgeze/Ornith-1.0-9B-1M-GGUF) | [35B](https://huggingface.co/satgeze/Ornith-1.0-35B-1M-GGUF)