Instructions to use bullerwins/Kimi-K3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use bullerwins/Kimi-K3-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 bullerwins/Kimi-K3-GGUF:MXFP4 # Run inference directly in the terminal: llama cli -hf bullerwins/Kimi-K3-GGUF:MXFP4
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf bullerwins/Kimi-K3-GGUF:MXFP4 # Run inference directly in the terminal: llama cli -hf bullerwins/Kimi-K3-GGUF:MXFP4
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 bullerwins/Kimi-K3-GGUF:MXFP4 # Run inference directly in the terminal: ./llama-cli -hf bullerwins/Kimi-K3-GGUF:MXFP4
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 bullerwins/Kimi-K3-GGUF:MXFP4 # Run inference directly in the terminal: ./build/bin/llama-cli -hf bullerwins/Kimi-K3-GGUF:MXFP4
Use Docker
docker model run hf.co/bullerwins/Kimi-K3-GGUF:MXFP4
- LM Studio
- Jan
- Ollama
How to use bullerwins/Kimi-K3-GGUF with Ollama:
ollama run hf.co/bullerwins/Kimi-K3-GGUF:MXFP4
- Unsloth Desktop
- Docker Model Runner
How to use bullerwins/Kimi-K3-GGUF with Docker Model Runner:
docker model run hf.co/bullerwins/Kimi-K3-GGUF:MXFP4
- Lemonade
How to use bullerwins/Kimi-K3-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull bullerwins/Kimi-K3-GGUF:MXFP4
Run and chat with the model
lemonade run user.Kimi-K3-GGUF-MXFP4
List all available models
lemonade list
- Atomic Chat
Add files using upload-large-folder tool
Browse files
.gitattributes
CHANGED
|
@@ -33,3 +33,7 @@ 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 |
+
mxfp4/Kimi-K3-mxfp4-00004-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
mxfp4/Kimi-K3-mxfp4-00001-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
mxfp4/Kimi-K3-mxfp4-00002-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
mxfp4/Kimi-K3-mxfp4-00003-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
Experimental version using https://github.com/ggml-org/llama.cpp/pull/26185
|
mxfp4/Kimi-K3-mxfp4-00001-of-00004.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4aa3769b234055b82b23523de13da1e03107fa93e11ee59575bb1ef7cdb66e7
|
| 3 |
+
size 445473457024
|
mxfp4/Kimi-K3-mxfp4-00002-of-00004.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:380021a93351800412a7c5f448b5f6c169fb252d967f4ec2fae8b0ead244d7d0
|
| 3 |
+
size 445466548512
|
mxfp4/Kimi-K3-mxfp4-00003-of-00004.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa59b6863d0ea6bc11d9bfc1ec4d6db544ec0187254453245522c0b73617c31e
|
| 3 |
+
size 445466548512
|
mxfp4/Kimi-K3-mxfp4-00004-of-00004.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82b511ccb14ff9ffe713f9c2c3ff54fbbdb5d870f09bb08e082333d302b78f07
|
| 3 |
+
size 224751299552
|