MiniCPM5-2B-SFT-Pashto-GGUF
GGUF quantizations of nassimjp/MiniCPM5-2B-SFT-Pashto, a fine-tuned version of openbmb/MiniCPM5-2B for Pashto language.
Quant Table
| File | Bits | Est. Size | Use Case |
|---|---|---|---|
| model_f16.gguf | 16 | ~4.6 GB | Reference / re-quantization |
| model_q8_0.gguf | 8 | ~2.4 GB | Max quality, enough RAM |
| model_q6_k.gguf | 6 | ~1.9 GB | High quality |
| model_q5_k_m.gguf | 5 | ~1.6 GB | Balanced |
| model_q5_k_s.gguf | 5 | ~1.6 GB | Balanced, smaller |
| model_q4_k_m.gguf | 4 | ~1.4 GB | Recommended |
| model_q4_k_s.gguf | 4 | ~1.3 GB | Lower RAM |
| model_q3_k_l.gguf | 3 | ~1.1 GB | Low RAM |
| model_q3_k_m.gguf | 3 | ~1.0 GB | Low RAM |
| model_q3_k_s.gguf | 3 | ~0.9 GB | Minimum quality |
| model_q2_k.gguf | 2 | ~0.7 GB | Very low RAM only |
VRAM / RAM Requirements
| Quant | RAM |
|---|---|
| Q8_0 | ~3 GB |
| Q4_K_M | ~2 GB |
| Q2_K | ~1.5 GB |
Usage
llama.cpp
./llama-cli -m model_q4_k_m.gguf -p "Your prompt here" -n 256
llama-cpp-python
from llama_cpp import Llama
llm = Llama(model_path="model_q4_k_m.gguf")
output = llm("Your prompt here", max_tokens=256)
print(output["choices"][0]["text"])
LM Studio
Download any .gguf file and load directly in LM Studio.
Ollama
ollama run hf.co/tinyopsec/MiniCPM5-2B-SFT-Pashto-GGUF:Q4_K_M
Notes
- Architecture:
LlamaForCausalLM - Fine-tuned for Pashto (پښتو) language
- Based on MiniCPM5-2B with hybrid reasoning (Think / No-Think modes)
- For llama.cpp, recommended:
--min-p 0.0to avoid repetition