mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF

1---2base_model: Proactive-Interactive-R1/Proactive-Interactive-R1-Math-7B-Max3language:4- en5library_name: transformers6mradermacher:7  readme_rev: 18quantized_by: mradermacher9---10## About11 12<!-- ### quantize_version: 2 -->13<!-- ### output_tensor_quantised: 1 -->14<!-- ### convert_type: hf -->15<!-- ### vocab_type:  -->16<!-- ### tags:  -->17<!-- ### quants:  x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->18<!-- ### quants_skip:  -->19<!-- ### skip_mmproj:  -->20static quants of https://huggingface.co/Proactive-Interactive-R1/Proactive-Interactive-R1-Math-7B-Max21 22<!-- provided-files -->23 24***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Proactive-Interactive-R1-Math-7B-Max-GGUF).***25 26weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.27## Usage28 29If you are unsure how to use GGUF files, refer to one of [TheBloke's30READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for31more details, including on how to concatenate multi-part files.32 33## Provided Quants34 35(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)36 37| Link | Type | Size/GB | Notes |38|:-----|:-----|--------:|:------|39| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.Q2_K.gguf) | Q2_K | 3.1 |  |40| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.Q3_K_S.gguf) | Q3_K_S | 3.6 |  |41| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |42| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.Q3_K_L.gguf) | Q3_K_L | 4.2 |  |43| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.IQ4_XS.gguf) | IQ4_XS | 4.4 |  |44| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |45| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |46| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.Q5_K_S.gguf) | Q5_K_S | 5.4 |  |47| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.Q5_K_M.gguf) | Q5_K_M | 5.5 |  |48| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.Q6_K.gguf) | Q6_K | 6.4 | very good quality |49| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |50| [GGUF](https://huggingface.co/mradermacher/Proactive-Interactive-R1-Math-7B-Max-GGUF/resolve/main/Proactive-Interactive-R1-Math-7B-Max.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |51 52Here is a handy graph by ikawrakow comparing some lower-quality quant53types (lower is better):54 55![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)56 57And here are Artefact2's thoughts on the matter:58https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec959 60## FAQ / Model Request61 62See https://huggingface.co/mradermacher/model_requests for some answers to63questions you might have and/or if you want some other model quantized.64 65## Thanks66 67I thank my company, [nethype GmbH](https://www.nethype.de/), for letting68me use its servers and providing upgrades to my workstation to enable69this work in my free time.70 71<!-- end -->72