--- base_model: - 152334H/miqu-1-70b-sf - lizpreciatior/lzlv_70b_fp16_hf language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About static quants of https://huggingface.co/wolfram/miquliz-120b-v2.0 weighted/imatrix quants available at https://huggingface.co/mradermacher/miquliz-120b-v2.0-i1-GGUF While other static and imatrix quants are available already, I wanted a wider selection of quants available for this model. ## 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/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q2_K.gguf) | Q2_K | 44.5 | | | [PART 1](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q3_K_XS.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q3_K_XS.gguf.split-ab) | Q3_K_XS | 49.2 | | | [PART 1](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q3_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q3_K_S.gguf.split-ab) | Q3_K_S | 52.1 | | | [PART 1](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q3_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q3_K_M.gguf.split-ab) | Q3_K_M | 58.1 | lower quality | | [PART 1](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q3_K_L.gguf.split-ab) | Q3_K_L | 63.3 | | | [PART 1](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q4_K_S.gguf.split-ab) | Q4_K_S | 68.6 | fast, medium quality | | [PART 1](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.IQ4_NL.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.IQ4_NL.gguf.split-ab) | IQ4_NL | 68.7 | fast, slightly worse than Q4_K_S | | [PART 1](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q4_K_M.gguf.split-ab) | Q4_K_M | 72.5 | fast, medium quality | | [PART 1](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q5_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q5_K_S.gguf.split-ab) | Q5_K_S | 83.1 | | | [PART 1](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q5_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q5_K_M.gguf.split-ab) | Q5_K_M | 85.3 | | | [PART 1](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q6_K.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q6_K.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q6_K.gguf.split-ac) | Q6_K | 99.0 | very good quality | | [PART 1](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q8_0.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q8_0.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/miquliz-120b-v2.0-GGUF/resolve/main/miquliz-120b-v2.0.Q8_0.gguf.split-ac) | Q8_0 | 128.1 | 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)