LegalParam Banner

LegalParam — GGUF

Legal · Indian Jurisprudence  |  BharatGenAI  |  हिन्दी + English

LegalParam is BharatGenAI's Indian legal domain specialist, trained on the Constitution of India, central and state acts, landmark Supreme Court and High Court judgments, IPC/BNS, CrPC/BNSS, and legal procedures.


Available Quantizations

Quantization File Size Description
F16 LegalParam-F16.gguf ~5.7 GB Full float 16, near-lossless, GPU recommended
Q2_K LegalParam-Q2_K.gguf ~0.9 GB 2-bit, smallest, significant quality loss
Q3_K_M LegalParam-Q3_K_M.gguf ~1.3 GB 3-bit medium, moderate quality
Q4_K_M LegalParam-Q4_K_M.gguf ~1.7 GB 4-bit medium — recommended for most users
Q5_K_M LegalParam-Q5_K_M.gguf ~2.0 GB 5-bit medium, great quality
Q6_K LegalParam-Q6_K.gguf ~2.4 GB 6-bit, excellent quality
Q8_0 LegalParam-Q8_0.gguf ~3.0 GB 8-bit, best quality/size balance

Not sure which to pick? → Q4_K_M for everyday use on CPU/GPU → Q8_0 for best quality on GPU with ≥ 6 GB VRAM → F16/BF16 for full precision research use


Use Cases

  • Indian constitutional law queries
  • IPC/BNS and CrPC/BNSS section lookup
  • Landmark Supreme Court judgment summaries
  • Legal rights advisory for citizens
  • Contract and property law guidance

Quick Start

llama.cpp

# Windows
winget install llama.cpp

# Run directly from Hugging Face
llama-cli -hf arunmcops/LegalParam-GGUF:LegalParam-Q4_K_M.gguf

# OpenAI-compatible server
llama-server -hf arunmcops/LegalParam-GGUF:LegalParam-Q4_K_M.gguf --port 8080

Ollama

ollama run hf.co/arunmcops/LegalParam-GGUF:LegalParam-Q4_K_M.gguf

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="arunmcops/LegalParam-GGUF",
    filename="LegalParam-Q4_K_M.gguf",
)
response = llm.create_chat_completion(
    messages=[{"role": "user", "content": "नमस्ते! आप कौन हैं?"}]
)
print(response["choices"][0]["message"]["content"])

About BharatGenAI

BharatGenAI builds open-source language models for India — bilingual (Hindi + English) and domain-specialized for agriculture, healthcare, legal, and general-purpose use.


License

Apache 2.0 — free for personal, research, and commercial use.

Downloads last month
219
GGUF
Model size
3B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support