--- base_model: PJMixers-Dev/Granite-3.1-Earthen-v0.3-3B-A800M datasets: - BeaverAI/REDACTED1 - BeaverAI/REDACTED2 - BeaverAI/REDACTED3 - BeaverAI/REDACTED4 - BeaverAI/REDACTED5 - BeaverAI/REDACTED6 - PJMixers-Dev/Lit-axo-Shuffled - PJMixers-Dev/Mielikki_Erebus-87k-axo - PJMixers/RyokoAI_Honeyfeed3600-Cleanish - PJMixers-Dev/allura-org_fujin-cleaned-stage-2-axo - Nelathan/synthetic-sugar-quill - PJMixers-Dev/winglian_visual-novels-json-axo-dropped-long - PJMixers-Dev/recursal_SCP-RECURSAL-Cleaned - PJMixers-Dev/Subtitles - PJMixers-Dev/KaraKaraWitch_AnimeSubtitle-axo - PJMixers/AP-News-2024 - PJMixers-Dev/Fundus-AP-News-Formatted - PJMixers-Dev/Fundus-AP-News-2-Formatted - PJMixers-Dev/goodwiki-2024-12-04-axo - epfl-llm/guidelines - PJMixers-Dev/allenai_tulu-3-sft-mixture-filtered-2-ShareGPT - OpenLeecher/lmsys_chat_1m_clean - PJMixers-Dev/Gryphe-Aesir-RPG-Charcards-Opus-Mixed - allura-org/gryphe-sonnet-3.5-charcards-names-added - anthracite-org/c2_logs_32k_llama3_qwen2_v1.3 - PJMixers-Dev/MinervaAI_Aesir-Preview-Anon - PJMixers-Dev/lemonilia_LimaRP-Simple-CustomShareGPT-Shuffled - Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned - PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT - PJMixers/OpenLeecher_Teatime_all_logs_longest-ShareGPT - grimulkan/aicg-logs-augmented - grimulkan/PIPPA-augmented-dedup - PJMixers/grimulkan_bluemoon_Karen_cleaned-carded-formatted - PJMixers/lodrick-the-lafted_OpusStories-ShareGPT - Gryphe/ChatGPT-4o-Writing-Prompts - Gryphe/Opus-WritingPrompts - anthracite-org/nopm_claude_writing_fixed - PJMixers-Dev/Tiefighter-13B-Fake-Distill-ShareGPT - allura-org/fujin-instruct-v2 - ToastyPigeon/gutenberg-sft - PocketDoc/Dans-Prosemaxx-Adventure - PocketDoc/Dans-Failuremaxx-Adventure-3 - TheDrummer/AmoralQA-v2 language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher --- ## About weighted/imatrix quants of https://huggingface.co/PJMixers-Dev/Granite-3.1-Earthen-v0.3-3B-A800M static quants are available at https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-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/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-Q2_K.gguf) | i1-Q2_K | 1.3 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.7 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.8 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.5 | | | [GGUF](https://huggingface.co/mradermacher/Granite-3.1-Earthen-v0.3-3B-A800M-i1-GGUF/resolve/main/Granite-3.1-Earthen-v0.3-3B-A800M.i1-Q6_K.gguf) | i1-Q6_K | 2.8 | practically like static Q6_K | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.