Jobim.ai Docs

JOBIM J-Factor Llama 70B

Optimized for complex reasoning. Our highest-capacity model.

Model Overview

Base Model
Llama 3 70B
Endpoint
/v1/models/jobim-jfactor-llama-70b

The J-Factor Advantage

Same quality as Llama 3 70B — 95.8% smaller, runs on a single H100.

95.8%
Compression
8.2 TPS
Throughput
131K
Context

Best For

  • CheckmarkCode generation & debugging
  • CheckmarkFinancial modeling
  • CheckmarkLong-form report generation
  • CheckmarkSpecialized fine-tuning
  • CheckmarkHigh-precision reasoning

Code Example

Python
from openai import OpenAI

client = OpenAI(
    api_key="your-jobim-key",
    base_url="https://api.jobim.ai/v1"
)

response = client.chat.completions.create(
    model="jobim-jfactor-llama-70b",
    messages=[{"role": "user", "content": "Write a Python web scraper."}]
)