Instructions to use Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF",
	filename="Moonlight-16B-A3B-Instruct-APEX-handroll.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 Myric/Moonlight-16B-A3B-Instruct-APEX-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 Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf Myric/Moonlight-16B-A3B-Instruct-APEX-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 Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Myric/Moonlight-16B-A3B-Instruct-APEX-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 Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF

Use Docker

docker model run hf.co/Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF

LM Studio
Jan

vLLM

How to use Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Myric/Moonlight-16B-A3B-Instruct-APEX-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": "Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF

Ollama
How to use Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF with Ollama:
```
ollama run hf.co/Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF
```

Unsloth Studio

How to use Myric/Moonlight-16B-A3B-Instruct-APEX-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 Myric/Moonlight-16B-A3B-Instruct-APEX-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 Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF with Docker Model Runner:
```
docker model run hf.co/Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF
```

Lemonade

How to use Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF

Run and chat with the model

lemonade run user.Moonlight-16B-A3B-Instruct-APEX-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Moonlight-16B-A3B-Instruct — APEX GGUF

MoE-aware, mixed-precision APEX quantizations of moonshotai/Moonlight-16B-A3B-Instruct (16B total / ~3B active, DeepSeek-V2/V3-style MoE: 64 routed + 2 shared experts, MLA attention).

APEX assigns quantization precision per tensor role and per layer instead of uniformly — keeping always-active shared experts and edge layers high-precision while compressing the sparse routed-expert middle layers hard. The result is near-full-precision quality at a fraction of the size.

Results

Perplexity on wikitext-2-raw (test split, 200 × 512-token windows), measured with llama-perplexity. Lower is better.

File	Size	BPW	PPL	Δ vs F16
F16 (reference baseline)	30 GB	16.0	8.836	—
APEX-i-quality	12 GB	5.99	8.916	+0.90%
APEX-handroll	11 GB	5.40	8.959	+1.38%

Both tiers hold within ~1% of full-precision perplexity at ~2.6× smaller. Coherent in English and on code prompts; ~85 tok/s generation on a single modern GPU.

Which file to pick

APEX-i-quality (12 GB) — highest quality; edge/near routed experts at Q6_K/Q5_K, middle at IQ4_XS, shared experts Q8_0, attention Q6_K. Uses a diverse ("I") imatrix.
APEX-handroll (11 GB) — same recipe, but the routed down projections are pinned to IQ4_NL (see Method). ~8% smaller for +0.05 PPL — the better size/quality trade on this architecture.

Usage (llama.cpp)

llama-cli   -m Moonlight-16B-A3B-Instruct-APEX-handroll.gguf -ngl 999 -p "Hello"
# or serve an OpenAI-compatible endpoint:
llama-server -m Moonlight-16B-A3B-Instruct-APEX-handroll.gguf -ngl 999 --host 0.0.0.0 --port 8081

Requires a llama.cpp build recent enough to support the deepseek2 architecture and the kimi-k2 pre-tokenizer (Moonlight shares Moonshot's tiktoken tokenizer).

Method & notes

APEX is a bit-allocation recipe over stock llama-quantize --tensor-type-file (no kernel/format changes). Two architecture-specific adaptations were required for Moonlight that the stock APEX profiles do not handle:

MLA attention tensors. Moonlight uses Multi-head Latent Attention, so its attention projections are named attn_q, attn_kv_a_mqa, attn_k_b, attn_v_b, attn_output — not the usual attn_q/k/v. The generated config was patched to assign precision to the real MLA tensors (otherwise the KV projections silently keep the base type).
Non-256-divisible expert dim (1408). Moonlight's routed-expert intermediate size is 1408, which K-quants (Q6_K/Q5_K/IQ4_XS require 256-divisibility) cannot quantize — they fall back to Q8_0, wasting bits on the largest tensors. The handroll tier pins routed ffn_down_exps to IQ4_NL (a block-32 4-bit type) to compress them properly. This is the difference between the two tiers.

Baseline: quantized from gabriellarson/Moonlight-16B-A3B-Instruct-GGUF's F16 conversion. Calibration imatrix built from Bartowski's calibration_datav3 (diverse chat/code/reasoning text).

Reproduce

Full recipe with exact commands, pinned tool versions, the tensor-type configs, and the config-generation/patch scripts is in REPRODUCE.md. Bundled: generate_config.sh, patch_moonlight_config.py, configs/moonlight_*.txt, and the imatrix — so the whole pipeline is reproducible without any private dependency.

Attribution & licenses

All components are MIT-licensed; see LICENSE and NOTICE.

Base model: Moonshot AI (@moonshotai) — Moonlight-16B-A3B-Instruct (MIT)
F16 GGUF conversion: gabriellarson (@gabriellarson) — source GGUF (MIT-derived)
Quantization engine: llama.cpp by the ggml authors (@ggml-org · github) (MIT)
APEX recipe & toolkit: Ettore Di Giacinto / LocalAI (@mudler) — localai-org/apex-quant (MIT)
Calibration data: Bartowski (@bartowski) — calibration_datav3

This is an unofficial community quantization and is not affiliated with or endorsed by Moonshot AI.

Downloads last month: 248

GGUF

Model size

16B params

Architecture

deepseek2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Myric/Moonlight-16B-A3B-Instruct-APEX-GGUF

Base model

moonshotai/Moonlight-16B-A3B-Instruct

Quantized

(8)

this model