--- license: apache-2.0 datasets: - allenai/dolma - allenai/tulu-v2-sft-mixture-olmo-4096 language: - en tags: - TensorBlock - GGUF base_model: hamishivi/OLMo-1B-0724-SFT-hf ---
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

## hamishivi/OLMo-1B-0724-SFT-hf - GGUF This repo contains GGUF format model files for [hamishivi/OLMo-1B-0724-SFT-hf](https://huggingface.co/hamishivi/OLMo-1B-0724-SFT-hf). The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5165](https://github.com/ggml-org/llama.cpp/commit/1d735c0b4fa0551c51c2f4ac888dd9a01f447985). ## Our projects
Awesome MCP Servers TensorBlock Studio
Project A Project B
A comprehensive collection of Model Context Protocol (MCP) servers. A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀 👀 See what we built 👀
## Prompt template ``` <|endoftext|><|user|> {prompt} <|assistant|> ``` ## Model file specification | Filename | Quant type | File Size | Description | | -------- | ---------- | --------- | ----------- | | [OLMo-1B-0724-SFT-hf-Q2_K.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q2_K.gguf) | Q2_K | 0.513 GB | smallest, significant quality loss - not recommended for most purposes | | [OLMo-1B-0724-SFT-hf-Q3_K_S.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q3_K_S.gguf) | Q3_K_S | 0.592 GB | very small, high quality loss | | [OLMo-1B-0724-SFT-hf-Q3_K_M.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q3_K_M.gguf) | Q3_K_M | 0.649 GB | very small, high quality loss | | [OLMo-1B-0724-SFT-hf-Q3_K_L.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q3_K_L.gguf) | Q3_K_L | 0.696 GB | small, substantial quality loss | | [OLMo-1B-0724-SFT-hf-Q4_0.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q4_0.gguf) | Q4_0 | 0.748 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [OLMo-1B-0724-SFT-hf-Q4_K_S.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q4_K_S.gguf) | Q4_K_S | 0.755 GB | small, greater quality loss | | [OLMo-1B-0724-SFT-hf-Q4_K_M.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q4_K_M.gguf) | Q4_K_M | 0.791 GB | medium, balanced quality - recommended | | [OLMo-1B-0724-SFT-hf-Q5_0.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q5_0.gguf) | Q5_0 | 0.895 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [OLMo-1B-0724-SFT-hf-Q5_K_S.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q5_K_S.gguf) | Q5_K_S | 0.895 GB | large, low quality loss - recommended | | [OLMo-1B-0724-SFT-hf-Q5_K_M.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q5_K_M.gguf) | Q5_K_M | 0.918 GB | large, very low quality loss - recommended | | [OLMo-1B-0724-SFT-hf-Q6_K.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q6_K.gguf) | Q6_K | 1.052 GB | very large, extremely low quality loss | | [OLMo-1B-0724-SFT-hf-Q8_0.gguf](https://huggingface.co/tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF/blob/main/OLMo-1B-0724-SFT-hf-Q8_0.gguf) | Q8_0 | 1.362 GB | very large, extremely low quality loss - not recommended | ## Downloading instruction ### Command line Firstly, install Huggingface Client ```shell pip install -U "huggingface_hub[cli]" ``` Then, downoad the individual model file the a local directory ```shell huggingface-cli download tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF --include "OLMo-1B-0724-SFT-hf-Q2_K.gguf" --local-dir MY_LOCAL_DIR ``` If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try: ```shell huggingface-cli download tensorblock/hamishivi_OLMo-1B-0724-SFT-hf-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf' ```