Store › model › LLM

DeepSeek-Coder-V2-Lite-Instruct-GGUF

Name: DeepSeek-Coder-V2-Lite-Instruct-GGUF
Author: bartowski

by bartowski · source Hugging Face · updated 2024-06-20

other9.7 GB~12 GB RAMsource aliveunlabeled

Llamacpp imatrix Quantizations of DeepSeek-Coder-V2-Lite-Instruct

Add to LogiShell Open in the web IDE

The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF
License: other (custom license: read it at the source before installing)
Requirements: about 12 GB of RAM, 9.7 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
Tags: gguf text-generation endpoints_compatible imatrix conversational

Numbers

384,832 downloads on Hugging Face
195 likes
license other
9.7 GB for DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf
327,838 npm downloads a week for node-llama-cpp
latest node-llama-cpp@3.22.1

Numbers as of 2026-10-02 21:00 UTC, from the source API.

Summary

Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.

Reviews

No reviews yet. Reviews are written inside LogiShell: open this card in the app.

Files

file	quant	size
`DeepSeek-Coder-V2-Lite-Instruct-IQ2_M.gguf`	IQ2_M	5.9 GB
`DeepSeek-Coder-V2-Lite-Instruct-IQ2_S.gguf`	IQ2_S	5.6 GB
`DeepSeek-Coder-V2-Lite-Instruct-IQ2_XS.gguf`	IQ2_XS	5.6 GB
`DeepSeek-Coder-V2-Lite-Instruct-IQ3_M.gguf`	IQ3_M	7.0 GB
`DeepSeek-Coder-V2-Lite-Instruct-IQ3_XS.gguf`	IQ3_XS	6.6 GB
`DeepSeek-Coder-V2-Lite-Instruct-IQ3_XXS.gguf`	IQ3_XXS	6.5 GB
`DeepSeek-Coder-V2-Lite-Instruct-IQ4_XS.gguf`	IQ4_XS	8.0 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q2_K.gguf`	Q2_K	6.0 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q3_K_L.gguf`	Q3_K_L	7.9 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q3_K_M.gguf`	Q3_K_M	7.6 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q3_K_S.gguf`	Q3_K_S	7.0 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q4_K_L.gguf`	Q4_K_L	10 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf`	Q4_K_M	9.7 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q4_K_S.gguf`	Q4_K_S	8.9 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q5_K_L.gguf`	Q5_K_L	12 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q5_K_M.gguf`	Q5_K_M	11 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q5_K_S.gguf`	Q5_K_S	10 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q6_K.gguf`	Q6_K	13 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q6_K_L.gguf`	Q6_K_L	14 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q8_0.gguf`	Q8_0	16 GB
`DeepSeek-Coder-V2-Lite-Instruct-Q8_0_L.gguf`	Q8_0	16 GB
`DeepSeek-Coder-V2-Lite-Instruct-f32.gguf/DeepSeek-Coder-V2-Lite-Instruct-f32-00001-of-00002.gguf`	F32	37 GB
`DeepSeek-Coder-V2-Lite-Instruct-f32.gguf/DeepSeek-Coder-V2-Lite-Instruct-f32-00002-of-00002.gguf`	F32	22 GB

From the source README

Llamacpp imatrix Quantizations of DeepSeek-Coder-V2-Lite-Instruct

Using llama.cpp release b3166 for quantization.

Original model: https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct

All quants made using imatrix option with dataset from here

Prompt format

{system_prompt}

User: {prompt}

Assistant: Assistant:
```

Download a file (not the whole branch) from below:

| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| DeepSeek-Coder-V2-Lite-Instruct-Q8_0_L.gguf | Q8_0_L | 17.09GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
| DeepSeek-Coder-V2-Lite-Instruct-Q8_0.gguf | Q8_0 | 16.70GB | Extremely high quality, generally unneeded but max available quant. |
| DeepSeek-Coder-V2-Lite-Instruct-Q6_K_L.gguf | Q6_K_L | 14.56GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
| DeepSeek-Coder-V2-Lite-Instruct-Q6_K.gguf | Q6_K | 14.06GB | Very high quality, near perfect, *recommended*. |
| [DeepSeek-Coder-V2-Lite-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Co…

Source: https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF

Card id model:hf:bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF · collected 2026-10-02 21:00 UTC · JSON