MaziyarPanahi / DeepSeek family / text-generation
DeepSeek-V3-0324-GGUF
MaziyarPanahi/DeepSeek-V3-0324-GGUF
Run locally Smallest indexed GGUF / needs Ollama
ollama run hf.co/MaziyarPanahi/DeepSeek-V3-0324-GGUF/DeepSeek-V3-0324.IQ1_S.gguf-00009-of-00009.gguf Benchmarks
Where it scores.
General Provisional —
Coding Provisional —
Math Provisional —
Reasoning Provisional —
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
| Precision | Format | Size | Params | File |
|---|---|---|---|---|
| Q4 / smallest | GGUF | 3 MB | — | DeepSeek-V3-0324.IQ1_S.gguf-00009-of-00009.gguf |
| Q4 | GGUF | 3 MB | — | DeepSeek-V3-0324.IQ1_M.gguf-00009-of-00009.gguf |
| Q4 | GGUF | 5 MB | — | DeepSeek-V3-0324.Q2_K.gguf-00009-of-00009.gguf |
| Q4 | GGUF | 6 MB | — | DeepSeek-V3-0324.Q3_K_S.gguf-00009-of-00009.gguf |
| Q4 | GGUF | 13.7 GB | — | DeepSeek-V3-0324.IQ1_S.gguf-00001-of-00009.gguf |
| Q4 | GGUF | 14.9 GB | — | DeepSeek-V3-0324.IQ1_M.gguf-00001-of-00009.gguf |
| Q4 | GGUF | 16.6 GB | — | DeepSeek-V3-0324.IQ1_S.gguf-00007-of-00009.gguf |
| Q4 | GGUF | 16.6 GB | — | DeepSeek-V3-0324.IQ1_S.gguf-00005-of-00009.gguf |
| Q4 | GGUF | 16.6 GB | — | DeepSeek-V3-0324.IQ1_S.gguf-00003-of-00009.gguf |
| Q4 | GGUF | 17.3 GB | — | DeepSeek-V3-0324.IQ1_S.gguf-00006-of-00009.gguf |
| Q4 | GGUF | 17.3 GB | — | DeepSeek-V3-0324.IQ1_S.gguf-00004-of-00009.gguf |
| Q4 | GGUF | 17.4 GB | — | DeepSeek-V3-0324.IQ1_S.gguf-00002-of-00009.gguf |
| Q4 | GGUF | 18.1 GB | — | DeepSeek-V3-0324.IQ1_S.gguf-00008-of-00009.gguf |
| Q4 | GGUF | 18.6 GB | — | DeepSeek-V3-0324.IQ1_M.gguf-00007-of-00009.gguf |
| Q4 | GGUF | 18.6 GB | — | DeepSeek-V3-0324.IQ1_M.gguf-00005-of-00009.gguf |
| Q4 | GGUF | 18.6 GB | — | DeepSeek-V3-0324.IQ1_M.gguf-00003-of-00009.gguf |
| Q4 | GGUF | 19.4 GB | — | DeepSeek-V3-0324.IQ1_M.gguf-00006-of-00009.gguf |
| Q4 | GGUF | 19.4 GB | — | DeepSeek-V3-0324.IQ1_M.gguf-00004-of-00009.gguf |
| Q4 | GGUF | 19.4 GB | — | DeepSeek-V3-0324.IQ1_M.gguf-00002-of-00009.gguf |
| Q4 | GGUF | 20.2 GB | — | DeepSeek-V3-0324.IQ1_M.gguf-00008-of-00009.gguf |
| Q4 | GGUF | 22.6 GB | — | DeepSeek-V3-0324.Q2_K.gguf-00001-of-00009.gguf |
| Q4 | GGUF | 26.7 GB | — | DeepSeek-V3-0324.Q3_K_S.gguf-00001-of-00009.gguf |
| Q4 | GGUF | 30.5 GB | — | DeepSeek-V3-0324.Q2_K.gguf-00007-of-00009.gguf |
| Q4 | GGUF | 30.5 GB | — | DeepSeek-V3-0324.Q2_K.gguf-00005-of-00009.gguf |
| Q4 | GGUF | 30.5 GB | — | DeepSeek-V3-0324.Q2_K.gguf-00003-of-00009.gguf |
| Q4 | GGUF | 32.1 GB | — | DeepSeek-V3-0324.Q2_K.gguf-00006-of-00009.gguf |
| Q4 | GGUF | 32.1 GB | — | DeepSeek-V3-0324.Q2_K.gguf-00004-of-00009.gguf |
| Q4 | GGUF | 32.2 GB | — | DeepSeek-V3-0324.Q2_K.gguf-00002-of-00009.gguf |
| Q4 | GGUF | 33.4 GB | — | DeepSeek-V3-0324.Q2_K.gguf-00008-of-00009.gguf |
| Q4 | GGUF | 36.3 GB | — | DeepSeek-V3-0324.Q3_K_S.gguf-00007-of-00009.gguf |
| Q4 | GGUF | 36.3 GB | — | DeepSeek-V3-0324.Q3_K_S.gguf-00005-of-00009.gguf |
| Q4 | GGUF | 36.3 GB | — | DeepSeek-V3-0324.Q3_K_S.gguf-00003-of-00009.gguf |
| Q4 | GGUF | 37.9 GB | — | DeepSeek-V3-0324.Q3_K_S.gguf-00006-of-00009.gguf |
| Q4 | GGUF | 37.9 GB | — | DeepSeek-V3-0324.Q3_K_S.gguf-00004-of-00009.gguf |
| Q4 | GGUF | 38.0 GB | — | DeepSeek-V3-0324.Q3_K_S.gguf-00002-of-00009.gguf |
| Q4 | GGUF | 39.5 GB | — | DeepSeek-V3-0324.Q3_K_S.gguf-00008-of-00009.gguf |
Sizes are file sizes, not peak runtime memory.
From the Hugging Face model card
About this model.
From the Hugging Face model card
About this model.
MaziyarPanahi/DeepSeek-V3-0324-GGUF
- Model creator: deepseek-ai
- Original model: deepseek-ai/DeepSeek-V3-0324
Description
MaziyarPanahi/DeepSeek-V3-0324-GGUF contains GGUF format model files for deepseek-ai/DeepSeek-V3-0324.
About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
- llama.cpp. The source project for GGUF. Offers a CLI and a server option.
- llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
- LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
- text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
- KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
- GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
- LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
- Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
- candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.
- ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
Special thanks
🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.