--- base_model: paperboygold/gpt-oss-sanguine-20b-v1 datasets: - NousResearch/Hermes-3-Dataset - Anthropic/hh-rlhf - teknium/OpenHermes-2.5 - microsoft/orca-math-word-problems-200k - WizardLM/WizardLM_evol_instruct_V2_196k - calme/legalkit - nvidia/Llama-3.1-Nemotron-70B-Instruct-HF - Yoondi/bluemoon-roleplay-chat-jsonl - LooksJuicy/Chinese-Roleplay-Novel - zhouzr/pk-roleplay - openerotica/long-roleplay-v0.1 - mrcuddle/nous-character-codex - Arasaaf/myuri_roleplay - AlekseyKorshuk/gpt-roleplay-realm-chatml - diwank/gpt_roleplay_realm-chatml - Gryphe/Sonnet3.5-Charcard-Roleplay - hieunguyenminh/roleplay - zerofata/Roleplay-Anime-Characters - Locutusque/FalseReject-sharegpt - QuixiAI/open-instruct-uncensored - allenai/WildChat-4.8M-Full - nvidia/Llama-Nemotron-Post-Training-Dataset - WizardLMTeam/WizardLM_evol_instruct_V2_196k - nvidia/OpenCodeReasoning - MaziyarPanahi/calme-legalkit-v0.2 - Nitral-AI/Cybersecurity-ShareGPT - savaniDhruv/Cybersecurity_Attack_Dataset - openerotica/erotica-analysis - demelin/moral_stories language: - en - zh library_name: transformers license: mit mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - peft - lora - roleplay - creative-writing - consequence-based-alignment - gpt-oss - openai-harmony --- ## About static quants of https://huggingface.co/paperboygold/gpt-oss-sanguine-20b-v1 ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gpt-oss-sanguine-20b-v1-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.Q3_K_S.gguf) | Q3_K_S | 12.2 | | | [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.Q2_K.gguf) | Q2_K | 12.2 | | | [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.IQ4_XS.gguf) | IQ4_XS | 12.3 | | | [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.Q3_K_M.gguf) | Q3_K_M | 13.0 | lower quality | | [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.Q3_K_L.gguf) | Q3_K_L | 13.4 | | | [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.Q4_K_S.gguf) | Q4_K_S | 14.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.Q4_K_M.gguf) | Q4_K_M | 15.9 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.Q5_K_S.gguf) | Q5_K_S | 16.0 | | | [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.Q5_K_M.gguf) | Q5_K_M | 17.0 | | | [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.Q6_K.gguf) | Q6_K | 22.3 | very good quality | | [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.Q8_0.gguf) | Q8_0 | 22.4 | fast, best quality | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.