mradermacher/Cloud-Coder-7B-R-GGUF

1---2base_model: tripincloud/Cloud-Coder-7B-R3language:4- en5library_name: transformers6license: apache-2.07quantized_by: mradermacher8---9## About10 11<!-- ### quantize_version: 2 -->12<!-- ### output_tensor_quantised: 1 -->13<!-- ### convert_type: hf -->14<!-- ### vocab_type:  -->15<!-- ### tags:  -->16static quants of https://huggingface.co/tripincloud/Cloud-Coder-7B-R17 18<!-- provided-files -->19weighted/imatrix quants are available at https://huggingface.co/mradermacher/Cloud-Coder-7B-R-i1-GGUF20## Usage21 22If you are unsure how to use GGUF files, refer to one of [TheBloke's23READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for24more details, including on how to concatenate multi-part files.25 26## Provided Quants27 28(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)29 30| Link | Type | Size/GB | Notes |31|:-----|:-----|--------:|:------|32| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.Q2_K.gguf) | Q2_K | 3.1 |  |33| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.Q3_K_S.gguf) | Q3_K_S | 3.6 |  |34| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |35| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.Q3_K_L.gguf) | Q3_K_L | 4.2 |  |36| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.IQ4_XS.gguf) | IQ4_XS | 4.4 |  |37| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |38| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |39| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.Q5_K_S.gguf) | Q5_K_S | 5.4 |  |40| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.Q5_K_M.gguf) | Q5_K_M | 5.5 |  |41| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.Q6_K.gguf) | Q6_K | 6.4 | very good quality |42| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |43| [GGUF](https://huggingface.co/mradermacher/Cloud-Coder-7B-R-GGUF/resolve/main/Cloud-Coder-7B-R.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |44 45Here is a handy graph by ikawrakow comparing some lower-quality quant46types (lower is better):47 48![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)49 50And here are Artefact2's thoughts on the matter:51https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec952 53## FAQ / Model Request54 55See https://huggingface.co/mradermacher/model_requests for some answers to56questions you might have and/or if you want some other model quantized.57 58## Thanks59 60I thank my company, [nethype GmbH](https://www.nethype.de/), for letting61me use its servers and providing upgrades to my workstation to enable62this work in my free time.63 64<!-- end -->65