Instructions to use ubergarm/Kimi-Dev-72B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ubergarm/Kimi-Dev-72B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ubergarm/Kimi-Dev-72B-GGUF",
	filename="Kimi-Dev-72B-smol-IQ3_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 ubergarm/Kimi-Dev-72B-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 ubergarm/Kimi-Dev-72B-GGUF
# Run inference directly in the terminal:
llama cli -hf ubergarm/Kimi-Dev-72B-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ubergarm/Kimi-Dev-72B-GGUF
# Run inference directly in the terminal:
llama cli -hf ubergarm/Kimi-Dev-72B-GGUF

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 ubergarm/Kimi-Dev-72B-GGUF
# Run inference directly in the terminal:
./llama-cli -hf ubergarm/Kimi-Dev-72B-GGUF

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 ubergarm/Kimi-Dev-72B-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ubergarm/Kimi-Dev-72B-GGUF

Use Docker

docker model run hf.co/ubergarm/Kimi-Dev-72B-GGUF

LM Studio
Jan

vLLM

How to use ubergarm/Kimi-Dev-72B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ubergarm/Kimi-Dev-72B-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": "ubergarm/Kimi-Dev-72B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ubergarm/Kimi-Dev-72B-GGUF

Ollama
How to use ubergarm/Kimi-Dev-72B-GGUF with Ollama:
```
ollama run hf.co/ubergarm/Kimi-Dev-72B-GGUF
```

Unsloth Studio

How to use ubergarm/Kimi-Dev-72B-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 ubergarm/Kimi-Dev-72B-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 ubergarm/Kimi-Dev-72B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ubergarm/Kimi-Dev-72B-GGUF to start chatting

How to use ubergarm/Kimi-Dev-72B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ubergarm/Kimi-Dev-72B-GGUF

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": "ubergarm/Kimi-Dev-72B-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ubergarm/Kimi-Dev-72B-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 ubergarm/Kimi-Dev-72B-GGUF

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 ubergarm/Kimi-Dev-72B-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ubergarm/Kimi-Dev-72B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ubergarm/Kimi-Dev-72B-GGUF

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ubergarm/Kimi-Dev-72B-GGUF" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use ubergarm/Kimi-Dev-72B-GGUF with Docker Model Runner:
```
docker model run hf.co/ubergarm/Kimi-Dev-72B-GGUF
```

Lemonade

How to use ubergarm/Kimi-Dev-72B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ubergarm/Kimi-Dev-72B-GGUF

Run and chat with the model

lemonade run user.Kimi-Dev-72B-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

`ik_llama.cpp` imatrix Quantizations of Kimi-Dev-72B

This quant collection REQUIRES ik_llama.cpp fork to support advanced non-linear SotA quants and Multi-Head Latent Attention (MLA). Do not download these big files and expect them to run on mainline vanilla llama.cpp, ollama, LM Studio, KoboldCpp, etc! Though might work in Nexesenex's croco.cpp kobold fork (untested).

NOTE ik_llama.cpp can also run your existing GGUFs from bartowski, unsloth, mradermacher, etc if you want to try it out before downloading my quants.

smol-IQ3_K 32.273 GiB (3.813 BPW)

type f32: 401 tensors
type q4_K: 1 tensors token_embd
type q6_K: 1 tensors output ("head")
type iq4_nl: 80 tensors down
type iq3_k: 320 tensors (q|o) (gate|up)
type iq4_k: 160 tensors (k|v)

Quickstart

# Clone
git clone git@github.com:ikawrakow/ik_llama.cpp.git
cd ik_llama.cpp

# Build (might try adding -DGGML_CUDA_IQK_FORCE_BF16=1 for 3090s and older)
cmake -B build -DGGML_CUDA=ON -DGGML_CUDA_F16=ON -DGGML_SCHED_MAX_COPIES=1
cmake --build build --config Release -j $(nproc)

# Run (set threads to number of CPU physical cores, mmap is fine for faster startup, adjust ctx/ngl as needed)
./build/bin/llama-server \
    --model /mnt/models/ubergarm/Kimi-Dev-72B-GGUF/Kimi-Dev-72B-smol-IQ3_K.gguf \
    --ctx-size 8192 \
    -ctk q8_0 -ctv q8_0 \
    -fa \
    --no-mmap \
    -ngl 48 \
    --threads 16 \
    --parallel 1 \
    --host 127.0.0.1 \
    --port 8080

Benchmarks

Speed

High-end Gaming Rig Hardware
- AMD 9950X
- Overclocked infinity fabric "gear 1" clocks
- 2x 48GB DDR5@6400 RAM (~87GB/s benchmarked)
- 3090 TI FE 24GB VRAM @ 450 Watts (uncapped)
PP ~500 tok/sec with 2k batches
TG ~5 tok/sec limited by RAM i/o bandwidth

./build/bin/llama-sweep-bench \
    --model /mnt/models/ubergarm/Kimi-Dev-72B-GGUF/Kimi-Dev-72B-smol-IQ3_K.gguf \
    --ctx-size 6144 \
    -ctk q8_0 -ctv q8_0 \
    -fa \
    --no-mmap \
    -ub 2048 -b 2048 \
    -ngl 48 \
    --warmup-batch \
    --threads 16

ubergarm/Kimmy-Dev-72B-smol-IQ3_K

PP	TG	N_KV	T_PP s	S_PP t/s	T_TG s	S_TG t/s
2048	512	0	3.925	521.77	103.624	4.94
2048	512	2048	4.058	504.63	105.265	4.86

Quality

I tested perplexity for a bunch of experimental quants, decided this one was a decent trade-off between quality and speed.

FAQ

Why is it smol?

I ran out of names making a bunch of similar sized quants for the Perplexity graph above lol.

Will you make larger GGUFs?

Naw, you can get good mainline llama.cpp GGUFs from others already like bartowski and bullerwins.

Where can I get those hot new EXL3 quants?

Check out ArtusDev's collection

What about the new iqK_kt QTIP Trellis style quants?

I may release something eventually, but they are still pretty fresh gonna wait a minute to see if any breaking changes happen before releasing.
Also the column dimension of the ffn_down tensor is not divisible by 256 so had to use iq4_nl unless something changes.

References

ik_llama.cpp

Downloads last month: 35

GGUF

Model size

73B params

Architecture

qwen2

Hardware compatibility

Model tree for ubergarm/Kimi-Dev-72B-GGUF

Base model

Qwen/Qwen2.5-72B

Finetuned

moonshotai/Kimi-Dev-72B

Quantized

(23)

this model

ik_llama.cpp imatrix Quantizations of Kimi-Dev-72B

smol-IQ3_K 32.273 GiB (3.813 BPW)

Quickstart

Benchmarks

Speed

ubergarm/Kimmy-Dev-72B-smol-IQ3_K

Quality

FAQ

References

Model tree for ubergarm/Kimi-Dev-72B-GGUF

`ik_llama.cpp` imatrix Quantizations of Kimi-Dev-72B