--- base_model: abacusai/Smaug-Llama-3-70B-Instruct-32K datasets: - aqua_rat - microsoft/orca-math-word-problems-200k - m-a-p/CodeFeedback-Filtered-Instruction language: - en library_name: transformers license: llama3 quantized_by: mradermacher --- ## About static quants of https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct-32K weighted/imatrix quants are available at https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-i1-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/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q2_K.gguf) | Q2_K | 26.5 | | | [GGUF](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.IQ3_XS.gguf) | IQ3_XS | 29.4 | | | [GGUF](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q3_K_S.gguf) | Q3_K_S | 31.0 | | | [GGUF](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.IQ3_M.gguf) | IQ3_M | 32.0 | | | [GGUF](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q3_K_L.gguf) | Q3_K_L | 37.2 | | | [GGUF](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.IQ4_XS.gguf) | IQ4_XS | 38.4 | | | [GGUF](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q5_K_S.gguf) | Q5_K_S | 48.8 | | | [GGUF](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q5_K_M.gguf) | Q5_K_M | 50.0 | | | [PART 1](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality | | [PART 1](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Smaug-Llama-3-70B-Instruct-32K-GGUF/resolve/main/Smaug-Llama-3-70B-Instruct-32K.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | 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) 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.