Llama-3.1-Nemotron-70B-Instruct-HF-GGUF

Original Model

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Run with LlamaEdge

  • LlamaEdge version: coming soon
  • Prompt template

    • Prompt type: llama-3-chat

    • Prompt string

      <|begin_of_text|><|start_header_id|>system<|end_header_id|>
      
      {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
      
      {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
      
      {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
      
      {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
      
  • Context size: 128000

  • Run as LlamaEdge service

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.1-Nemotron-70B-Instruct-HF-Q5_K_M.gguf \
      llama-api-server.wasm \
      --prompt-template llama-3-chat \
      --ctx-size 128000 \
      --model-name Llama-3.1-Nemotron-70b
    
  • Run as LlamaEdge command app

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.1-Nemotron-70B-Instruct-HF-Q5_K_M.gguf \
      llama-chat.wasm \
      --prompt-template llama-3-chat \
      --ctx-size 128000
    

Quantized GGUF Models

Name Quant method Bits Size Use case
Llama-3.1-Nemotron-70B-Instruct-HF-Q2_K.gguf Q2_K 2 26.4 GB smallest, significant quality loss - not recommended for most purposes
Llama-3.1-Nemotron-70B-Instruct-HF-Q3_K_L.gguf Q3_K_L 3 37.1 GB small, substantial quality loss
Llama-3.1-Nemotron-70B-Instruct-HF-Q3_K_M.gguf Q3_K_M 3 34.3 GB very small, high quality loss
Llama-3.1-Nemotron-70B-Instruct-HF-Q3_K_S.gguf Q3_K_S 3 30.9 GB very small, high quality loss
Llama-3.1-Nemotron-70B-Instruct-HF-Q4_0.gguf Q4_0 4 40 GB legacy; small, very high quality loss - prefer using Q3_K_M
Llama-3.1-Nemotron-70B-Instruct-HF-Q4_K_M.gguf Q4_K_M 4 42.5 GB medium, balanced quality - recommended
Llama-3.1-Nemotron-70B-Instruct-HF-Q4_K_S.gguf Q4_K_S 4 40.3 GB small, greater quality loss
Llama-3.1-Nemotron-70B-Instruct-HF-Q5_0.gguf Q5_0 5 48.7 GB legacy; medium, balanced quality - prefer using Q4_K_M
Llama-3.1-Nemotron-70B-Instruct-HF-Q5_K_M.gguf Q5_K_M 5 49.9 GB large, very low quality loss - recommended
Llama-3.1-Nemotron-70B-Instruct-HF-Q5_K_S.gguf Q5_K_S 5 48.7 GB large, low quality loss - recommended
Llama-3.1-Nemotron-70B-Instruct-HF-Q6_K-00001-of-00002.gguf Q6_K 6 29.8 GB very large, extremely low quality loss
Llama-3.1-Nemotron-70B-Instruct-HF-Q6_K-00002-of-00002.gguf Q6_K 6 28.0 GB very large, extremely low quality loss
Llama-3.1-Nemotron-70B-Instruct-HF-Q8_0-00001-of-00003.gguf Q8_0 8 29.8 GB very large, extremely low quality loss - not recommended
Llama-3.1-Nemotron-70B-Instruct-HF-Q8_0-00002-of-00003.gguf Q8_0 8 29.8 GB very large, extremely low quality loss - not recommended
Llama-3.1-Nemotron-70B-Instruct-HF-Q8_0-00003-of-00003.gguf Q8_0 8 15.4 GB very large, extremely low quality loss - not recommended
Llama-3.1-Nemotron-70B-Instruct-HF-f16-00001-of-00005.gguf f16 16 30.0 GB
Llama-3.1-Nemotron-70B-Instruct-HF-f16-00002-of-00005.gguf f16 16 29.6 GB
Llama-3.1-Nemotron-70B-Instruct-HF-f16-00003-of-00005.gguf f16 16 29.6 GB
Llama-3.1-Nemotron-70B-Instruct-HF-f16-00004-of-00005.gguf f16 16 29.6 GB
Llama-3.1-Nemotron-70B-Instruct-HF-f16-00005-of-00005.gguf f16 16 22.2 GB

Quantized with llama.cpp 3932.

Downloads last month
170
GGUF
Model size
70.6B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for second-state/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF