# Cortex-ai by Abdoulaye Coumbassa: Open-Weight Model Source: https://savrn.com/models/cortex-ai Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Cortex-ai (1.7T parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 3301.0 GB | 3961.2 GB | More than one server of any accelerator the SAVRN Index prices. | | | | 8-bit | 1650.5 GB | 1980.6 GB | 8x [MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) (256 GB) Vultr | $16.00 | [7x MI355X](https://savrn.com/ai-index/pricing/gpus/mi355x) $18.13 · [8x B300](https://savrn.com/ai-index/pricing/gpus/b300) $52.80 | | 4-bit | 825.2 GB | 990.3 GB | 4x [MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) (256 GB) Vultr | $8.00 | [4x MI355X](https://savrn.com/ai-index/pricing/gpus/mi355x) $10.36 · [6x MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) $11.10 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [Cortex-ai on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/cortex-ai/gpus) ## Model Card By Abdoulaye Coumbassa, published under mit, revision e1985aeed6fe. ### CORTEX CORTEX is an artificial intelligence built by Frankenstein-Labs to help people learn, create, program and move forward with technology. Model: CORTEX Developer: Frankenstein-Labs Focus: AI for development, learning and assistance CORTEX is designed for students, young developers, researchers, creators and users of all ages who want to understand and use modern technology. It helps write code, explain concepts, analyse projects, find and fix errors, prepare for exams and carry a project through from idea to working software. « J'ai créé CORTEX pour aider les nouvelles générations à apprendre, créer et construire leur avenir avec la technologie. » — Abdoulaye Coumbassa, founder of Frankenstein-Labs ### What CORTEX does [Read the full model card (1,066 words)](https://savrn.com/models/cortex-ai/card) ## Configuration Architecture DeepseekV4ForCausalLM Context length (tokens) 1,048,576 Layers 61 Hidden size 7,168 Attention heads 128 Key/value heads 1 Head dimension 512 Vocabulary size 129,280 Routed experts 384 Experts active per token 6 Sliding window (tokens) 128 RoPE base 10,000 Stored precision bfloat16 Model type deepseek_v4 Quantization fp8 ## Identity and Version Repository Frankenstein-Labs/Cortex-ai Publisher Abdoulaye Coumbassa Task Text generation Modality Text Library transformers Parameters 1.7T parameters Languages fr, en, zh Revision e1985aeed6feaf79bc0a224bc8d11ded0813e7e4 First published 2026-09-16 Last updated 2026-09-26 ## Files and Weights 164 files, 892.8 GB in total. The weights are 66 files totalling 892.7 GB in safetensors. Weights66 files · 892.7 GB Configuration70 files · 11.9 MB Tokenizer2 files · 6.4 MB Documentation17 files · 85.9 KB Other7 files · 11.9 KB Repository2 files · 1.7 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00066.safetensors | Weights | 1.9 GB | 74ff60e30429 | | model-00002-of-00066.safetensors | Weights | 13.9 GB | d7be184a5582 | | model-00003-of-00066.safetensors | Weights | 13.9 GB | fc9291c02445 | | model-00004-of-00066.safetensors | Weights | 13.9 GB | 6f2c6511e5cc | | model-00005-of-00066.safetensors | Weights | 13.9 GB | 453aeaf23b4c | | model-00006-of-00066.safetensors | Weights | 13.9 GB | 9a1ea3ba51ac | | model-00007-of-00066.safetensors | Weights | 13.9 GB | 1ac789c43cbf | | model-00008-of-00066.safetensors | Weights | 13.9 GB | b2e31dda0b24 | | model-00009-of-00066.safetensors | Weights | 13.9 GB | b2efb301a7e2 | | model-00010-of-00066.safetensors | Weights | 13.9 GB | 9f0d7228d9f9 | | model-00011-of-00066.safetensors | Weights | 13.9 GB | 9ff42cf9b641 | | model-00012-of-00066.safetensors | Weights | 13.9 GB | c50346bb61a3 | | model-00013-of-00066.safetensors | Weights | 13.9 GB | e4fd1c5c65e0 | | model-00014-of-00066.safetensors | Weights | 13.9 GB | a72fd0426270 | | model-00015-of-00066.safetensors | Weights | 13.9 GB | ca601d33d249 | | model-00016-of-00066.safetensors | Weights | 13.9 GB | f3ce6de8fbb5 | | model-00017-of-00066.safetensors | Weights | 13.9 GB | 4af598f3672a | | model-00018-of-00066.safetensors | Weights | 13.9 GB | 0313cffc575c | | model-00019-of-00066.safetensors | Weights | 13.9 GB | 5ea603dbdab6 | | model-00020-of-00066.safetensors | Weights | 13.9 GB | c3bb54f871d8 | | model-00021-of-00066.safetensors | Weights | 13.9 GB | 516167a84b4b | | model-00022-of-00066.safetensors | Weights | 13.9 GB | df3975926bf3 | | model-00023-of-00066.safetensors | Weights | 13.9 GB | e444e6d51548 | | model-00024-of-00066.safetensors | Weights | 13.9 GB | 8690577cde63 | | model-00025-of-00066.safetensors | Weights | 13.9 GB | 170edd2db317 | | model-00026-of-00066.safetensors | Weights | 13.9 GB | b3dcaa3372a4 | | model-00027-of-00066.safetensors | Weights | 13.9 GB | 50d385e1e247 | | model-00028-of-00066.safetensors | Weights | 13.9 GB | 0449120425ee | | model-00029-of-00066.safetensors | Weights | 13.9 GB | 37e8b8bcb439 | | model-00030-of-00066.safetensors | Weights | 13.9 GB | f9bc11eef0b4 | | model-00031-of-00066.safetensors | Weights | 13.9 GB | f115720429d7 | | model-00032-of-00066.safetensors | Weights | 13.9 GB | 7ac9402f531e | | model-00033-of-00066.safetensors | Weights | 13.9 GB | dcb6e9370ec5 | | model-00034-of-00066.safetensors | Weights | 13.9 GB | 607f907a970a | | model-00035-of-00066.safetensors | Weights | 13.9 GB | ca4454ca96c5 | | model-00036-of-00066.safetensors | Weights | 13.9 GB | 4ac44a65a92d | | model-00037-of-00066.safetensors | Weights | 13.9 GB | 6aad5ecd60cd | | model-00038-of-00066.safetensors | Weights | 13.9 GB | b8e9376eeba0 | | model-00039-of-00066.safetensors | Weights | 13.9 GB | 5182b6d508d4 | | model-00040-of-00066.safetensors | Weights | 13.9 GB | dc91a11234ee | | model-00041-of-00066.safetensors | Weights | 13.9 GB | 1b446abc23a0 | | model-00042-of-00066.safetensors | Weights | 13.9 GB | 5ec38fcfe390 | | model-00043-of-00066.safetensors | Weights | 13.9 GB | a9279341f553 | | model-00044-of-00066.safetensors | Weights | 13.9 GB | ef67de8c818b | | model-00045-of-00066.safetensors | Weights | 13.9 GB | 5830f22254b5 | | model-00046-of-00066.safetensors | Weights | 13.9 GB | 22ae4fcc55b9 | | model-00047-of-00066.safetensors | Weights | 13.9 GB | 30890437fc59 | | model-00048-of-00066.safetensors | Weights | 13.9 GB | 877e6060d9c1 | | model-00049-of-00066.safetensors | Weights | 13.9 GB | 0527cff3c52c | | model-00050-of-00066.safetensors | Weights | 13.9 GB | 52a94fd51d93 | | model-00051-of-00066.safetensors | Weights | 13.9 GB | 50044649fa7d | | model-00052-of-00066.safetensors | Weights | 13.9 GB | 086f263f3f49 | | model-00053-of-00066.safetensors | Weights | 13.9 GB | 5e0264fd0c71 | | model-00054-of-00066.safetensors | Weights | 13.9 GB | 3f3adcbb18ea | | model-00055-of-00066.safetensors | Weights | 13.9 GB | 5d4ab723dfab | | model-00056-of-00066.safetensors | Weights | 13.9 GB | 409be8499d63 | | model-00057-of-00066.safetensors | Weights | 13.9 GB | 75146b06c0eb | | model-00058-of-00066.safetensors | Weights | 13.9 GB | c3bbbde96d32 | | model-00059-of-00066.safetensors | Weights | 13.9 GB | 2f5b62cd3111 | | model-00060-of-00066.safetensors | Weights | 13.9 GB | 0e4ac232d193 | | model-00061-of-00066.safetensors | Weights | 13.9 GB | dc3ef841f627 | | model-00062-of-00066.safetensors | Weights | 13.9 GB | c8d8ecc7bc03 | | model-00063-of-00066.safetensors | Weights | 1.9 GB | 56193a52a6fc | | model-00064-of-00066.safetensors | Weights | 14.0 GB | 3869820fbd71 | | model-00065-of-00066.safetensors | Weights | 13.9 GB | 09268dadf4bb | | model-00066-of-00066.safetensors | Weights | 14.1 GB | 40d4bf1620bd | | config.json | Configuration | 2.0 KB | — | | configs/vision_projector.json | Configuration | 473 B | — | | conftest.py | Configuration | 254 B | — | | cortex_ai/__init__.py | Configuration | 1.2 KB | — | | cortex_ai/adapters/__init__.py | Configuration | 189 B | — | | cortex_ai/adapters/base.py | Configuration | 1.3 KB | — | | cortex_ai/adapters/hf_adapter.py | Configuration | 3.0 KB | — | | cortex_ai/adapters/mock.py | Configuration | 3.1 KB | — | | cortex_ai/api/__init__.py | Configuration | 285 B | — | | cortex_ai/api/serve.py | Configuration | 843 B | — | | cortex_ai/api/server.py | Configuration | 6.7 KB | — | | cortex_ai/behavior.py | Configuration | 4.1 KB | — | | cortex_ai/client.py | Configuration | 3.3 KB | — | | cortex_ai/config.py | Configuration | 5.2 KB | — | | cortex_ai/engine/__init__.py | Configuration | 249 B | — | | cortex_ai/engine/agent.py | Configuration | 5.8 KB | — | | cortex_ai/engine/dsml.py | Configuration | 3.0 KB | — | | cortex_ai/identity.py | Configuration | 2.9 KB | — | | cortex_ai/orchestration/__init__.py | Configuration | 1.0 KB | — | | cortex_ai/orchestration/engine.py | Configuration | 1.6 KB | — | | cortex_ai/orchestration/errors.py | Configuration | 1.0 KB | — | | cortex_ai/orchestration/finance.py | Configuration | 1.4 KB | — | | cortex_ai/orchestration/gateway.py | Configuration | 1.9 KB | — | | cortex_ai/orchestration/jobs.py | Configuration | 2.0 KB | — | | cortex_ai/orchestration/policy.py | Configuration | 1.1 KB | — | | cortex_ai/orchestration/providers.py | Configuration | 2.4 KB | — | | cortex_ai/orchestration/router.py | Configuration | 2.7 KB | — | | cortex_ai/orchestration/schemas.py | Configuration | 2.4 KB | — | | cortex_ai/orchestration/tooling.py | Configuration | 901 B | — | | cortex_ai/tools/__init__.py | Configuration | 369 B | — | | cortex_ai/tools/registry.py | Configuration | 7.2 KB | — | | cortex_ai/training/__init__.py | Configuration | 391 B | — | | cortex_ai/training/config.py | Configuration | 3.7 KB | — | | cortex_ai/training/dataset.py | Configuration | 5.8 KB | — | | cortex_ai/training/train.py | Configuration | 5.0 KB | — | | cortex_ai/vision/__init__.py | Configuration | 1.5 KB | — | | cortex_ai/vision/bridge.py | Configuration | 3.1 KB | — | | cortex_ai/vision/config.json | Configuration | 1.7 KB | — | | cortex_ai/vision/core.py | Configuration | 5.3 KB | — | | cortex_ai/vision/native.py | Configuration | 4.8 KB | — | | cortex_ai/vision/train.py | Configuration | 11.3 KB | — | | encoding/encoding_dsv4.py | Configuration | 29.0 KB | — | | encoding/test_encoding_dsv4.py | Configuration | 3.7 KB | — | | encoding/tests/test_input_1.json | Configuration | 2.7 KB | — | | encoding/tests/test_input_2.json | Configuration | 526 B | — | | encoding/tests/test_input_3.json | Configuration | 4.5 KB | — | | encoding/tests/test_input_4.json | Configuration | 2.7 KB | — | | examples/cortex_chat.py | Configuration | 1.5 KB | — | | examples/train_vision_projector.py | Configuration | 6.1 KB | — | | examples/vision_adapter.py | Configuration | 850 B | — | | examples/vision_bridge.py | Configuration | 884 B | — | | generation_config.json | Configuration | 170 B | — | | inference/config.json | Configuration | 1.2 KB | — | | inference/convert.py | Configuration | 6.6 KB | — | | inference/generate.py | Configuration | 6.7 KB | — | | inference/kernel.py | Configuration | 22.2 KB | — | | inference/model.py | Configuration | 45.1 KB | — | | model.safetensors.index.json | Configuration | 11.7 MB | 2de2ac1e4313 | | tests/test_agent.py | Configuration | 4.7 KB | — | | tests/test_api.py | Configuration | 4.6 KB | — | | tests/test_config.py | Configuration | 2.3 KB | — | | tests/test_cortex_architecture.py | Configuration | 1.2 KB | — | | tests/test_identity.py | Configuration | 1.1 KB | — | | tests/test_native_fusion.py | Configuration | 2.0 KB | — | | tests/test_orchestration.py | Configuration | 2.0 KB | — | | tests/test_projector_training.py | Configuration | 10.8 KB | — | | tests/test_tools.py | Configuration | 3.6 KB | — | | tests/test_training.py | Configuration | 4.0 KB | — | | tests/test_vision_bridge.py | Configuration | 710 B | — | | tools/shard_integrity.py | Configuration | 3.3 KB | — | | AGENTS.md | Documentation | 8.2 KB | — | | LICENSE | Documentation | 1.1 KB | — | | README.md | Documentation | 9.0 KB | — | | docs/README.fr.md | Documentation | 4.7 KB | — | | docs/affinage.fr.md | Documentation | 5.5 KB | — | | docs/api.fr.md | Documentation | 5.6 KB | — | | docs/architecture.fr.md | Documentation | 7.5 KB | — | | docs/charte-comportement.fr.md | Documentation | 971 B | — | | docs/encodage.fr.md | Documentation | 7.3 KB | — | | docs/guide-demarrage.fr.md | Documentation | 6.5 KB | — | | docs/identite-api.fr.md | Documentation | 803 B | — | | docs/inference-distribuee.fr.md | Documentation | 6.6 KB | — | | docs/orchestration.fr.md | Documentation | 2.3 KB | — | | docs/vision.fr.md | Documentation | 5.6 KB | — | | docs/vision_projector_training.md | Documentation | 4.2 KB | — | | encoding/README.md | Documentation | 9.2 KB | — | | inference/README.md | Documentation | 951 B | — | | data/cortex_sft.jsonl | Other | 2.8 KB | — | | encoding/tests/test_output_1.txt | Other | 2.4 KB | — | | encoding/tests/test_output_2.txt | Other | 342 B | — | | encoding/tests/test_output_3.txt | Other | 3.3 KB | — | | encoding/tests/test_output_4.txt | Other | 2.6 KB | — | | inference/requirements.txt | Other | 108 B | — | | requirements-ecosystem.txt | Other | 384 B | — | | .gitattributes | Repository | 1.6 KB | — | | .gitignore | Repository | 148 B | — | | tokenizer.json | Tokenizer | 6.4 MB | — | | tokenizer_config.json | Tokenizer | 801 B | — | ## License and Download License mit Access Open weights, no gate Download size 892.7 GB [Download from Abdoulaye Coumbassa](https://huggingface.co/Frankenstein-Labs/Cortex-ai) Released by Abdoulaye Coumbassa through its official repository on Hugging Face. [Read the license](https://opensource.org/license/mit). ## Built From - Derived from deepseek-ai/DeepSeek-V4-Pro-0813 - Described by [arXiv:2606.19348](https://savrn.com/papers/deepseek-v4-towards-highly-efficient-million-token-context-intelligence) - Quantized from deepseek-ai/DeepSeek-V4-Pro-0813 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 892.7 GB | | 16-bit | 3301.0 GB | | 8-bit | 1650.5 GB | | 4-bit | 825.2 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About Cortex-ai ### How much GPU memory does Cortex-ai need? About 3961.2 GB at 16-bit and 990.3 GB at 4-bit: the weights (1.7T parameters) plus a working margin. A long context needs more. ### Can I use Cortex-ai commercially? Yes. Cortex-ai is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included. ### What is Cortex-ai's context length? 1,048,576 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [DeepSeek-V4-Pro-0813](https://savrn.com/models/deepseek-v4-pro-0813) [SAIFI INDUSTRIES](https://savrn.com/model-publishers/saifiindustries) DeepSeek-V4-Pro-0813 is the official release of DeepSeek-V4-Pro, superseding the preview version, with greatly enhanced agentic capabilities and performance improvements that are especially pronounced in production environments. It is built on the DeepSeek-V4-Pro (Preview) model structure, with a DSpark speculative decoding module attached. DeepSeek-V4-Pro-0813 outperforms DeepSeek-V4-Pro (Preview) on the benchmarks listed below, and is broadly competitive with the strongest proprietary models available. 1. For the code-agent tasks among the public benchmarks above, DeepSeek-V4-Pro-0813 is evaluated with the minimal mode of DeepSeek Harness as the agent framework, using the max reasoning… Open weights mit 1.7T parameters 1,048,576 tokens transformers [View model](https://savrn.com/models/deepseek-v4-pro-0813) Model · Text generation ### [MiMo-V2.6-Pro-RL-UNCENSORED](https://savrn.com/models/mimo-v2-6-pro-rl-uncensored) [Dealign.ai](https://savrn.com/model-publishers/dealignai) Compliance-tuned drop-in replacement for XiaomiMiMo/MiMo-V2.6-Pro-RL. Refusal removed at the weight level. Vision, audio, and the DFlash speculative-decoding head fully preserved. Both enablethinking: true and enablethinking: false supported. The compliance number that matters for uplift research is the per-category rate on the four hard-uplift buckets — chem/bio, cybercrime, misinformation, and physical/technical harm — not the whole-320 average. Copyright and speech-act categories drag the "all-320" number down; they are not what this bundle is for. All four uplift categories clear ≥ 95 %. Cyber and chem/bio in particular land in the range where a technical uplift request is answered on… Open weights mit 1T parameters 1,048,576 tokens transformers [View model](https://savrn.com/models/mimo-v2-6-pro-rl-uncensored) Model · Text generation ### [GLM-5.3](https://savrn.com/models/glm-5-3) [Z.ai](https://savrn.com/model-publishers/zai-org) GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks: GLM-5.3 supports deployment with the following frameworks. Feel free to try them out: - SGLang — see cookbook - vLLM — see recipes - TokenSpeed — see here - Transformers — see transformers docs - KTransformers — see tutorial - Unsloth — see guide - For deployment on the Ascend NPU platform, inference frameworks such as vLLM-Ascend, xLLM and SGLang are supported — see here. - GLM-5.3 supports controlling the thinking budget through the reasoningeffort parameter, which accepts three levels: low, high, and max. It defaults to max… Open weights other 753.3B parameters 1,048,576 tokens transformers [View model](https://savrn.com/models/glm-5-3) Model · Text generation ### [GLM-5.2-FP8](https://savrn.com/models/glm-5-2-fp8) [Z.ai](https://savrn.com/model-publishers/zai-org) Join our WeChat or Discord community. Check out the GLM-5.2 blog and GLM-5 Technical report. Use GLM-5.2 API services on Z.ai API Platform. Try GLM-5.2 here. [ Paper ] [ GitHub ] We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a solid 1M-token context. GLM-5.2's new capabilities include: GLM-5.2 supports deployment with the following frameworks. Feel free to try them out: - SGLang (v0.5.13.post1+) — see cookbook - vLLM (v0.23.0+) — see recipes - Transformers (v0.5.12+) — see transformers docs - KTransformers (v0.5.12+)… Open weights mit 753.3B parameters 1,048,576 tokens transformers [View model](https://savrn.com/models/glm-5-2-fp8) Model · Text generation ### [GLM-5.2](https://savrn.com/models/glm-5-2) [Z.ai](https://savrn.com/model-publishers/zai-org) Join our WeChat or Discord community. Check out the GLM-5.2 blog and GLM-5 Technical report. Use GLM-5.2 API services on Z.ai API Platform. Try GLM-5.2 here. [ Paper ] [ GitHub ] We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a solid 1M-token context. GLM-5.2's new capabilities include: GLM-5.2 supports deployment with the following frameworks. Feel free to try them out: - SGLang (v0.5.13.post1+) — see cookbook - vLLM (v0.23.0+) — see recipes - Transformers (v0.5.12+) — see transformers docs - KTransformers (v0.5.12+)… Open weights mit 753.3B parameters 1,048,576 tokens transformers [View model](https://savrn.com/models/glm-5-2) Model · Text generation ### [not-a-GLM-5.3-backup](https://savrn.com/models/not-a-glm-5-3-backup) [Michael Fielding](https://savrn.com/model-publishers/mfielding92) GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks: GLM-5.3 supports deployment with the following frameworks. Feel free to try them out: - SGLang — see cookbook - vLLM — see recipes - TokenSpeed — see here - Transformers — see transformers docs - KTransformers — see tutorial - Unsloth — see guide - For deployment on the Ascend NPU platform, inference frameworks such as vLLM-Ascend, xLLM and SGLang are supported — see here. - GLM-5.3 supports controlling the thinking budget through the reasoningeffort parameter, which accepts three levels: low, high, and max. It defaults to max… Open weights other 753.3B parameters 1,048,576 tokens transformers [View model](https://savrn.com/models/not-a-glm-5-3-backup) ## Abdoulaye Coumbassa [All models and datasets](https://savrn.com/model-publishers/frankenstein-labs) ## Versions - [e1985aeed6fe](https://savrn.com/models/cortex-ai/versions/e1985aeed6fe) · current 2026-09-26 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [All models under mit](https://savrn.com/models/licenses/mit) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-09-26. - [Hugging Face record](https://huggingface.co/Frankenstein-Labs/Cortex-ai) - [How the hub is built](https://savrn.com/model-hub/methodology)