Instructions to use gaianet/SmolLM3-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gaianet/SmolLM3-3B-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="gaianet/SmolLM3-3B-GGUF") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("gaianet/SmolLM3-3B-GGUF") model = AutoModelForMultimodalLM.from_pretrained("gaianet/SmolLM3-3B-GGUF") - llama-cpp-python
How to use gaianet/SmolLM3-3B-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="gaianet/SmolLM3-3B-GGUF", filename="SmolLM3-3B-Q2_K.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use gaianet/SmolLM3-3B-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf gaianet/SmolLM3-3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf gaianet/SmolLM3-3B-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf gaianet/SmolLM3-3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf gaianet/SmolLM3-3B-GGUF:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf gaianet/SmolLM3-3B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf gaianet/SmolLM3-3B-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf gaianet/SmolLM3-3B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf gaianet/SmolLM3-3B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/gaianet/SmolLM3-3B-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use gaianet/SmolLM3-3B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "gaianet/SmolLM3-3B-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gaianet/SmolLM3-3B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/gaianet/SmolLM3-3B-GGUF:Q4_K_M
- SGLang
How to use gaianet/SmolLM3-3B-GGUF with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "gaianet/SmolLM3-3B-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gaianet/SmolLM3-3B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "gaianet/SmolLM3-3B-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gaianet/SmolLM3-3B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use gaianet/SmolLM3-3B-GGUF with Ollama:
ollama run hf.co/gaianet/SmolLM3-3B-GGUF:Q4_K_M
- Unsloth Studio
How to use gaianet/SmolLM3-3B-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for gaianet/SmolLM3-3B-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for gaianet/SmolLM3-3B-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for gaianet/SmolLM3-3B-GGUF to start chatting
- Pi
How to use gaianet/SmolLM3-3B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf gaianet/SmolLM3-3B-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "gaianet/SmolLM3-3B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use gaianet/SmolLM3-3B-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf gaianet/SmolLM3-3B-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default gaianet/SmolLM3-3B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- Docker Model Runner
How to use gaianet/SmolLM3-3B-GGUF with Docker Model Runner:
docker model run hf.co/gaianet/SmolLM3-3B-GGUF:Q4_K_M
- Lemonade
How to use gaianet/SmolLM3-3B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull gaianet/SmolLM3-3B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.SmolLM3-3B-GGUF-Q4_K_M
List all available models
lemonade list
Update models
Browse files- .gitattributes +13 -0
- SmolLM3-3B-Q2_K.gguf +3 -0
- SmolLM3-3B-Q3_K_L.gguf +3 -0
- SmolLM3-3B-Q3_K_M.gguf +3 -0
- SmolLM3-3B-Q3_K_S.gguf +3 -0
- SmolLM3-3B-Q4_0.gguf +3 -0
- SmolLM3-3B-Q4_K_M.gguf +3 -0
- SmolLM3-3B-Q4_K_S.gguf +3 -0
- SmolLM3-3B-Q5_0.gguf +3 -0
- SmolLM3-3B-Q5_K_M.gguf +3 -0
- SmolLM3-3B-Q5_K_S.gguf +3 -0
- SmolLM3-3B-Q6_K.gguf +3 -0
- SmolLM3-3B-Q8_0.gguf +3 -0
- SmolLM3-3B-f16.gguf +3 -0
- config.json +108 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,16 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
SmolLM3-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
SmolLM3-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
SmolLM3-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
SmolLM3-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
SmolLM3-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
SmolLM3-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
SmolLM3-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
SmolLM3-3B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
SmolLM3-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
SmolLM3-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
SmolLM3-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
SmolLM3-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
SmolLM3-3B-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
SmolLM3-3B-Q2_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd731a9146ea06d6ff81f407c34a13a38ef55c9a43bd4a50e31896b5666d97cd
|
| 3 |
+
size 1253301696
|
SmolLM3-3B-Q3_K_L.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e9b92fc149a3f48152a082a8b0928f18149aab8c946d594fb46cd269ce5d0be
|
| 3 |
+
size 1690213824
|
SmolLM3-3B-Q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a938969da291c0cad1aab210b905659ea279ed4cb7d56a02fc3ae32f55dd1313
|
| 3 |
+
size 1571069376
|
SmolLM3-3B-Q3_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b2296dc172cc41145042a1c6317b36afa858d9de28f7937a5e53c670e0d1840
|
| 3 |
+
size 1432313280
|
SmolLM3-3B-Q4_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf8242306ff85bf4c86d7f84e4cb11871beb17b2c1c27a79772dd2b8a2cd92c0
|
| 3 |
+
size 1805819328
|
SmolLM3-3B-Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a69ce14f4327d71da1d0654c92e6ff15c720a1236e3a8d43fc91d82ebfa9a1e
|
| 3 |
+
size 1915305408
|
SmolLM3-3B-Q4_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b629fdece6893f7a504d455f1c9f04693adebb7489eb21fbb44970f3329869a
|
| 3 |
+
size 1817615808
|
SmolLM3-3B-Q5_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4945a211d9dbc62d12891d2f897f383be683dd50a9f35b6581db68dcbf0c586d
|
| 3 |
+
size 2157354432
|
SmolLM3-3B-Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:185930ee1efe313b8f5d2fb8cd9d37071f147459fadac13f475cdc8c18fb0bf1
|
| 3 |
+
size 2213756352
|
SmolLM3-3B-Q5_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f78567e01e602eb69231e9b80148161ba94894b8e3ec4061cc779543be3991e
|
| 3 |
+
size 2157354432
|
SmolLM3-3B-Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17b5a5055fb984979af858d013f86484529b4abd9aec0aa880cc0090f332219c
|
| 3 |
+
size 2530860480
|
SmolLM3-3B-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5f32c61ea29450085ba2f1d7ce3458d28956c33208c280656a5b32386ce14b1
|
| 3 |
+
size 3275574720
|
SmolLM3-3B-f16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:621e8b953b22dd194f10d3fa2a41a6ea944867839c5d3be017d15549203dc70b
|
| 3 |
+
size 6158339520
|
config.json
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SmolLM3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 128000,
|
| 8 |
+
"eos_token_id": 128012,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
+
"max_position_embeddings": 65536,
|
| 52 |
+
"max_window_layers": 28,
|
| 53 |
+
"mlp_bias": false,
|
| 54 |
+
"model_type": "smollm3",
|
| 55 |
+
"no_rope_layer_interval": 4,
|
| 56 |
+
"no_rope_layers": [
|
| 57 |
+
1,
|
| 58 |
+
1,
|
| 59 |
+
1,
|
| 60 |
+
0,
|
| 61 |
+
1,
|
| 62 |
+
1,
|
| 63 |
+
1,
|
| 64 |
+
0,
|
| 65 |
+
1,
|
| 66 |
+
1,
|
| 67 |
+
1,
|
| 68 |
+
0,
|
| 69 |
+
1,
|
| 70 |
+
1,
|
| 71 |
+
1,
|
| 72 |
+
0,
|
| 73 |
+
1,
|
| 74 |
+
1,
|
| 75 |
+
1,
|
| 76 |
+
0,
|
| 77 |
+
1,
|
| 78 |
+
1,
|
| 79 |
+
1,
|
| 80 |
+
0,
|
| 81 |
+
1,
|
| 82 |
+
1,
|
| 83 |
+
1,
|
| 84 |
+
0,
|
| 85 |
+
1,
|
| 86 |
+
1,
|
| 87 |
+
1,
|
| 88 |
+
0,
|
| 89 |
+
1,
|
| 90 |
+
1,
|
| 91 |
+
1,
|
| 92 |
+
0
|
| 93 |
+
],
|
| 94 |
+
"num_attention_heads": 16,
|
| 95 |
+
"num_hidden_layers": 36,
|
| 96 |
+
"num_key_value_heads": 4,
|
| 97 |
+
"pad_token_id": 128004,
|
| 98 |
+
"pretraining_tp": 2,
|
| 99 |
+
"rms_norm_eps": 1e-06,
|
| 100 |
+
"rope_scaling": null,
|
| 101 |
+
"rope_theta": 5000000.0,
|
| 102 |
+
"sliding_window": null,
|
| 103 |
+
"torch_dtype": "bfloat16",
|
| 104 |
+
"transformers_version": "4.54.0.dev0",
|
| 105 |
+
"use_cache": false,
|
| 106 |
+
"use_sliding_window": false,
|
| 107 |
+
"vocab_size": 128256
|
| 108 |
+
}
|