Instructions to use KittenML/kitten-tts-2 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 KittenML/kitten-tts-2 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 KittenML/kitten-tts-2 # Run inference directly in the terminal: llama cli -hf KittenML/kitten-tts-2
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf KittenML/kitten-tts-2 # Run inference directly in the terminal: llama cli -hf KittenML/kitten-tts-2
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 KittenML/kitten-tts-2 # Run inference directly in the terminal: ./llama-cli -hf KittenML/kitten-tts-2
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 KittenML/kitten-tts-2 # Run inference directly in the terminal: ./build/bin/llama-cli -hf KittenML/kitten-tts-2
Use Docker
docker model run hf.co/KittenML/kitten-tts-2
- LM Studio
- Jan
- Ollama
How to use KittenML/kitten-tts-2 with Ollama:
ollama run hf.co/KittenML/kitten-tts-2
- Unsloth Desktop
- Docker Model Runner
How to use KittenML/kitten-tts-2 with Docker Model Runner:
docker model run hf.co/KittenML/kitten-tts-2
- Lemonade
How to use KittenML/kitten-tts-2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull KittenML/kitten-tts-2
Run and chat with the model
lemonade run user.kitten-tts-2-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Update the language model to the mixed_v1_rl checkpoint
Browse filesSame architecture and token layout; weights only. Rebuilt from the 2026-10-06 TL2 bundle: the dense bf16 and the 1.58-bit packing are reconstructed from tl2_emb16, the emb4 file is the bundle's own.
The previous model stays available on the v1 branch.
- lm/model-ternary.safetensors +1 -1
- lm/model-tl2-emb4.safetensors +2 -2
- lm/model.safetensors +1 -1
lm/model-ternary.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 954467780
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dd6cc318c16cbb177dd44d92521955d3abaa84a8910aae9ffb312c5ae920054
|
| 3 |
size 954467780
|
lm/model-tl2-emb4.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26faa1f7fc07a880d00bba49826789c867e57f0aacfaf934f722b0d13a041212
|
| 3 |
+
size 492114331
|
lm/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3469120704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5283cfe80ef17f6311d0d550fb96066bf02a98ec35c6c0aa41aafdc78d2beaa6
|
| 3 |
size 3469120704
|