second-state/SmolLM3-3B-GGUF
0552
<!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end -->
SmolLM3-3B-GGUF
Original Model
Run with LlamaEdge
- LlamaEdge version: v0.24.0 and above
- Prompt template
- Normal chat
- Prompt type:
smol3-no-think
- Prompt string
<|im_start|>system
## Metadata
Knowledge Cutoff Date: June 2025
Today Date: 15 July 2025
Reasoning Mode: /no_think
## Custom Instructions
You are a helpful AI assistant named SmolLM, trained by Hugging Face.
<|im_end|>
<|im_start|>user
{user_message_1}
<|im_end|>
<|im_start|>assistant
{assistant_message_1}
<|im_end|>
<|im_start|>user
{user_message_2}
<|im_end|>
<|im_start|>assistant- Chat with Tools
- Prompt type:
smol3-no-think
- Prompt string
<|im_start|>system
## Metadata
Knowledge Cutoff Date: June 2025
Today Date: 15 July 2025
Reasoning Mode: /no_think
## Custom Instructions
You are a helpful AI assistant named SmolLM, trained by Hugging Face.
### Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"name":"sum","description":"Calculate the sum of two numbers","parameters":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"a":{"description":"The left hand side number","format":"int32","type":"integer"},"b":{"description":"The right hand side number","format":"int32","type":"integer"}},"required":["a","b"],"title":"SumRequest","type":"object"}}
{"name":"sub","description":"Calculate the difference of two numbers","parameters":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"a":{"description":"The left hand side number","format":"int32","type":"integer"},"b":{"description":"The right hand side number","format":"int32","type":"integer"}},"required":["a","b"],"title":"SubRequest","type":"object"}}
{"name":"get_current_weather","description":"Get the weather for a given city","parameters":{"$schema":"http://json-schema.org/draft-07/schema#","definitions":{"TemperatureUnit":{"enum":["celsius","fahrenheit"],"type":"string"}},"properties":{"location":{"description":"the city to get the weather for, e.g., 'Beijing', 'New York', 'Tokyo'","type":"string"},"unit":{"$ref":"#/definitions/TemperatureUnit","description":"the unit to use for the temperature, e.g., 'celsius', 'fahrenheit'"}},"required":["location","unit"],"title":"GetWeatherRequest","type":"object"}}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
<|im_end|>
<|im_start|>user
{user_message_1}
<|im_end|>
<|im_start|>assistant
{assistant_message_1}
<|im_end|>
<|im_start|>user
{user_message_2}
<|im_end|>
<|im_start|>assistant <!-- - think mode
- Prompt type:
smol3-think
- Prompt string
<|im_start|>system
/think
## Custom Instructions
{system_message}
<|im_end|>
<|im_start|>user
{user_message_1}
<|im_end|>
<|im_start|>assistant
<think>
{think content}
</think>
{assistant_message_1}
<|im_end|>
<|im_start|>user
{user_message_2}
<|im_end|>
<|im_start|>assistant
<think>
{think content}
</think>
{assistant_message_2}
<|im_end|> -->- Context size:
128000
- Run as LlamaEdge service
wasmedge --dir .:. --nn-preload default:GGML:AUTO:SmolLM3-3B-Q5_K_M.gguf \
llama-api-server.wasm \
--model-name SmolLM3-3B \
--prompt-template smol3-no-think \
--ctx-size 128000- Run as LlamaEdge command app
wasmedge --dir .:. --nn-preload default:GGML:AUTO:SmolLM3-3B-Q5_K_M.gguf \
llama-chat.wasm \
--prompt-template smol3-no-think \
--ctx-size 128000Quantized GGUF Models
Quantized with llama.cpp b5889
