--- base_model: Delta-Vector/Hamanasu-Magnum-QwQ-32B datasets: - NewEden/Orion-LIT - NewEden/Orion-Asstr-Stories-16K - Mielikki/Erebus-87k - NewEden/RP-logs-V2-Experimental-prefixed - NewEden/Creative_Writing-Complexity - NewEden/Discord-Filtered - NewEden/DeepseekRP-Filtered - NewEden/Storium-Prefixed-Clean - NewEden/Basket-Weaving-Filtered - NewEden/LIMARP-Complexity - NewEden/Misc-Data-Sharegpt-Prefixed - NewEden/BlueSky-10K-Complexity - NewEden/OpenCAI-ShareGPT - NewEden/Basket-Weaving-Filtered - PocketDoc/Dans-Personamaxx-VN - PocketDoc/Dans-Kinomaxx-VanillaBackrooms - PocketDoc/Dans-Personamaxx-Logs - anthracite-org/kalo-opus-instruct-22k-no-refusal - lodrick-the-lafted/kalo-opus-instruct-3k-filtered - anthracite-org/nopm_claude_writing_fixed - anthracite-org/kalo_opus_misc_240827 - anthracite-org/kalo_misc_part2 - NewEden/Claude-Instruct-5K - NewEden/Claude-Instruct-2.7K language: - en library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - qwen - roleplay - finetune - storywriting --- ## About weighted/imatrix quants of https://huggingface.co/Delta-Vector/Hamanasu-Magnum-QwQ-32B ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hamanasu-Magnum-QwQ-32B-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-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/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | | | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | 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.