---
license: apache-2.0
language:
- en
- th
base_model:
- iapp/chinda-qwen3-4b
pipeline_tag: text-generation
library_name: transformers
tags:
- text-generation-inference
---

# **Chinda-Qwen3-4B-F32-GGUF**

> Chinda Opensource Thai LLM 4B is iApp Technology's cutting-edge Thai language model that brings advanced thinking capabilities to the Thai AI ecosystem. Built on the latest Qwen3-4B architecture, Chinda represents our commitment to developing sovereign AI solutions for Thailand.

## Model Files

| File | Size | Format |
|------|------|--------|
| Chinda-Qwen3-4B-F32.F32.gguf | 16.1 GB | 32-bit float |
| Chinda-Qwen3-4B-F32.BF16.gguf | 8.05 GB | BFloat16 |
| Chinda-Qwen3-4B-F32.F16.gguf | 8.05 GB | 16-bit float |
| Chinda-Qwen3-4B-F32.Q8_0.gguf | 4.28 GB | 8-bit quantized |
| Chinda-Qwen3-4B-F32.Q6_K.gguf | 3.31 GB | 6-bit quantized |
| Chinda-Qwen3-4B-F32.Q5_K_M.gguf | 2.89 GB | 5-bit quantized (medium) |
| Chinda-Qwen3-4B-F32.Q5_K_S.gguf | 2.82 GB | 5-bit quantized (small) |
| Chinda-Qwen3-4B-F32.Q4_K_M.gguf | 2.5 GB | 4-bit quantized (medium) |
| Chinda-Qwen3-4B-F32.Q4_K_S.gguf | 2.38 GB | 4-bit quantized (small) |
| Chinda-Qwen3-4B-F32.Q3_K_L.gguf | 2.24 GB | 3-bit quantized (large) |
| Chinda-Qwen3-4B-F32.Q3_K_M.gguf | 2.08 GB | 3-bit quantized (medium) |
| Chinda-Qwen3-4B-F32.Q3_K_S.gguf | 1.89 GB | 3-bit quantized (small) |
| Chinda-Qwen3-4B-F32.Q2_K.gguf | 1.67 GB | 2-bit quantized |

## Quants Usage 

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

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)