Hugging Face CommunityOpen Weights
BGE-M3-Math-Nexus-Agent
Math Model • Released 2024-11-6 • Last Verified 2025-02-01
BGE-M3-Math-Nexus-Agent - Fine-tuned and quantized Math domain model variant optimized for fast local host inference.
Context Window32k-128k
LicenseApache-2.0 / Community Open Source
Deployment
Local Model
API AvailableNo
Benchmark Performance
Math Domain Score79
Hardware Requirements for Local Running
Requires 24GB VRAM
Strengths
- •High accuracy
- •Fast inference
Limitations & Weaknesses
- •Closed source API
API Sample CodePython / REST
import openai
client = openai.OpenAI()
response = client.chat.completions.create(
model="bge-m3-math-nexus-agent",
messages=[
{"role": "system", "content": "You are a helpful expert assistant."},
{"role": "user", "content": "Explain quantum computing in 2 sentences."}
]
)
print(response.choices[0].message.content)Pricing Overview
Free Open Source (Hugging Face / Ollama)
Prices subject to provider tiers and volume discounts. Check documentation for current token rates.
Model Tags
#math#ollama#huggingface#quantized#local
Similar Models from Hugging Face Community
Meta AI
Open Weights
Llama 3.3 70B
Open Weights LLM
Llama 3.3 70B - Meta AI open source model engineered for high efficiency, vision, and edge performance.
Context Window128k
MMLU65
Cloud API Local Run
#meta#llama
Meta AI
Open Weights
Llama 3.2 11B Vision
Vision LLM
Llama 3.2 11B Vision - Meta AI open source model engineered for high efficiency, vision, and edge performance.
Context Window128k
MMLU66
Cloud API Local Run
#meta#llama
Meta AI
Open Weights
Llama 3.2 90B Vision
Vision LLM
Llama 3.2 90B Vision - Meta AI open source model engineered for high efficiency, vision, and edge performance.
Context Window128k
MMLU67
Cloud API Local Run
#meta#llama