Instructions to use unsloth/KernelLLM-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/KernelLLM-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="unsloth/KernelLLM-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/KernelLLM-GGUF")
model = AutoModelForCausalLM.from_pretrained("unsloth/KernelLLM-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/KernelLLM-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 unsloth/KernelLLM-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/KernelLLM-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/KernelLLM-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/KernelLLM-GGUF:UD-Q4_K_XL

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 unsloth/KernelLLM-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/KernelLLM-GGUF:UD-Q4_K_XL

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 unsloth/KernelLLM-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/KernelLLM-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/KernelLLM-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/KernelLLM-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/KernelLLM-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": "unsloth/KernelLLM-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/KernelLLM-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/KernelLLM-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 "unsloth/KernelLLM-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": "unsloth/KernelLLM-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 "unsloth/KernelLLM-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": "unsloth/KernelLLM-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/KernelLLM-GGUF with Ollama:
```
ollama run hf.co/unsloth/KernelLLM-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/KernelLLM-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 unsloth/KernelLLM-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 unsloth/KernelLLM-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/KernelLLM-GGUF to start chatting

Docker Model Runner
How to use unsloth/KernelLLM-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/KernelLLM-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/KernelLLM-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/KernelLLM-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.KernelLLM-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Atomic Chat

danielhanchen commited on May 19, 2025

Commit

29c2551

verified ·

1 Parent(s): ef61342

Add files using upload-large-folder tool

Browse files

Files changed (7) hide show

.gitattributes +6 -0
KernelLLM-Q2_K.gguf +3 -0
KernelLLM-Q6_K.gguf +3 -0
KernelLLM-UD-IQ1_M.gguf +3 -0
KernelLLM-UD-IQ2_M.gguf +3 -0
KernelLLM-UD-IQ2_XXS.gguf +3 -0
KernelLLM-UD-IQ3_XXS.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -39,3 +39,9 @@ KernelLLM-UD-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 KernelLLM-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 KernelLLM-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 KernelLLM-UD-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text

 KernelLLM-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 KernelLLM-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 KernelLLM-UD-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+KernelLLM-UD-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+KernelLLM-UD-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+KernelLLM-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+KernelLLM-UD-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+KernelLLM-UD-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+KernelLLM-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

KernelLLM-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f26e14e055067bec8df2101f68f3db65ff8db546fdc90206b8304ea4f8904296
+size 3179132672

KernelLLM-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:28be158fee13b8ef90d6ce36c98a2dc9c18781aa2b6a76d762e0ce534ddf28f9
+size 6596007680

KernelLLM-UD-IQ1_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:32531401472ab1a82495a4171d955ab208aab39c6ced5982827f5d853b8e3f24
+size 2292201216

KernelLLM-UD-IQ2_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:af9f6d38b4ae25ac7359a8ff83dc69019acb2be7939e359e2019b78e3d6f2991
+size 3003266816

KernelLLM-UD-IQ2_XXS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:917a6dd45b3214c3236943eeecf5b67b59c3c690af39beaaae75d35ca5a193eb
+size 2504865536

KernelLLM-UD-IQ3_XXS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c026ae52450ccbef5ff1363989f5fd1fcc3a12af56125594b78bbbf181dbb7f8
+size 3321771776