---
language: [vi]
license: apache-2.0
base_model: steve-nguyen/aai-accountant-tt133-v1.1
tags: [gguf, q4_k_m, llama-cpp, ollama, lm-studio, accounting, vietnamese, thông-tư-133]
quantized_by: llama.cpp
---
# AAI Accountant TT133 v1.1 — GGUF Q4\_K\_M

Converted with **llama.cpp** `convert_hf_to_gguf.py` + `llama-quantize`.  
Fully compatible with **Ollama** and **LM Studio**.

## Files

| File | Quant | Size |
|------|-------|------|
| `aai-accountant-tt133-Q4_K_M.gguf` | Q4\_K\_M | ~2.5GB |

## Ollama

```bash
ollama pull hf.co/steve-nguyen/aai-accountant-tt133-v1.1-GGUF:Q4_K_M
ollama run  hf.co/steve-nguyen/aai-accountant-tt133-v1.1-GGUF:Q4_K_M
```

## LM Studio

Search `steve-nguyen/aai-accountant-tt133-v1.1-GGUF` → Download `Q4_K_M`.