Llama 3.3 70B Instruct

Facts

Released

2024-11-26 the day the repository was first published on Hugging Face Hugging Face, read 2026-09-24

Licence

llama3.3 the licence the model card declares Hugging Face, read 2026-09-24

Open weights

Yes the weights are published in this Hugging Face repository, behind the maker's access form Hugging Face, read 2026-09-24

Parameters

70.6 billion counted from the safetensors weight files Hugging Face, read 2026-09-24

Active parameters

Unknown

Knowledge cutoff

2023-12-31 the knowledge cutoff OpenRouter lists OpenRouter, read 2026-09-24

Context window

• 131,072 tokens the maximum position embeddings in the model configuration model configuration, read 2026-09-24
• 131,072 tokens the context length OpenRouter lists OpenRouter, read 2026-09-24

Longest output

• 16,384 tokens the largest output OpenRouter's first provider allows OpenRouter, read 2026-09-24

Tool calling

• Yes the chat template in the tokenizer configuration accepts tool definitions Hugging Face, read 2026-09-24
• Yes OpenRouter lists tools among the supported parameters OpenRouter, read 2026-09-24

Structured output

• Yes OpenRouter lists structured outputs among the supported parameters OpenRouter, read 2026-09-24

Reasoning controls

Unknown

Inputs and outputs

text in, text out Hugging Face, read 2026-09-24

Good for

No source names a use.

Prices

Run it on your own hardware

Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.

Start it with a local runtime

• Ollama

  ollama run hf.co/MaziyarPanahi/Llama-3.3-70B-Instruct-GGUF:Q4_K_S

• LM Studio

  lms get MaziyarPanahi/Llama-3.3-70B-Instruct-GGUF
  lms server start

• llama.cpp server

  llama-server -hf MaziyarPanahi/Llama-3.3-70B-Instruct-GGUF:Q4_K_S --jinja

• vLLM

  vllm serve meta-llama/Llama-3.3-70B-Instruct

• SGLang

  sglang serve --model-path meta-llama/Llama-3.3-70B-Instruct --port 30000

Use it from your harness

Set up for CloudFerro Sherlock with the model meta-llama/Llama-3.3-70B-Instruct. Each endpoint page has the same setup for its own address.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "cloudferro-sherlock": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "CloudFerro Sherlock",
      "options": {
        "baseURL": "https://api-sherlock.cloudferro.com/openai/v1",
        "apiKey": "{env:CLOUDFERRO_SHERLOCK_API_KEY}"
      },
      "models": {
        "meta-llama/Llama-3.3-70B-Instruct": {
          "name": "Llama 3.3 70B Instruct",
          "limit": {
            "context": 131072,
            "output": 16384
          }
        }
      }
    }
  }
}

{
  "providers": {
    "cloudferro-sherlock": {
      "baseUrl": "https://api-sherlock.cloudferro.com/openai/v1",
      "api": "openai-completions",
      "apiKey": "$CLOUDFERRO_SHERLOCK_API_KEY",
      "models": [
        {
          "id": "meta-llama/Llama-3.3-70B-Instruct"
        }
      ]
    }
  }
}

Other ways to reach it

• Crusoe, model meta-llama/Llama-3.3-70B-Instruct
• Hugging Face, model meta-llama/Llama-3.3-70B-Instruct
• IO.NET, model meta-llama/Llama-3.3-70B-Instruct
• Kilo Gateway, model meta-llama/llama-3.3-70b-instruct
• Meganova, model meta-llama/Llama-3.3-70B-Instruct
• NanoGPT, model meta-llama/llama-3.3-70b-instruct
• NovitaAI, model meta-llama/llama-3.3-70b-instruct
• OpenRouter, model meta-llama/llama-3.3-70b-instruct
• Pioneer, model meta-llama/Llama-3.3-70B-Instruct
• CoreWeave, model meta-llama/Llama-3.3-70B-Instruct
• Ollama, model hf.co/MaziyarPanahi/Llama-3.3-70B-Instruct-GGUF:Q4_K_S

Published results

These are results other people published. Baltor did not run them and does not rank models by them.

• Results the maker published on the model card published by meta-llama Hugging Face, read 2026-09-24
• Artificial Analysis Coding Index: 11.9 published by Artificial Analysis OpenRouter, read 2026-09-24