Instructions to use Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Ma7ee7/MeetInstruct-0.6B-v1.5-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 Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M

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 Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M

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 Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ma7ee7/MeetInstruct-0.6B-v1.5-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": "Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M

Ollama
How to use Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF with Ollama:
```
ollama run hf.co/Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF with Docker Model Runner:
```
docker model run hf.co/Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M
```

Lemonade

How to use Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MeetInstruct-0.6B-v1.5-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

MeetInstruct-0.6B-v1.5 GGUF

GGUF conversions of Ma7ee7/MeetInstruct-0.6B-v1.5.

The model is based on Qwen3-0.6B and uses its ChatML-compatible chat template.

Files

File	Size
`MeetInstruct-0.6B-v1.5-F16.gguf`	1439.4 MiB
`MeetInstruct-0.6B-v1.5-Q8_0.gguf`	767.5 MiB
`MeetInstruct-0.6B-v1.5-Q6_K.gguf`	593.9 MiB
`MeetInstruct-0.6B-v1.5-Q5_K_M.gguf`	525.8 MiB
`MeetInstruct-0.6B-v1.5-Q5_K_S.gguf`	518.4 MiB
`MeetInstruct-0.6B-v1.5-Q4_K_M.gguf`	461.8 MiB
`MeetInstruct-0.6B-v1.5-Q4_K_S.gguf`	449.0 MiB
`MeetInstruct-0.6B-v1.5-Q3_K_L.gguf`	415.2 MiB
`MeetInstruct-0.6B-v1.5-Q3_K_M.gguf`	394.8 MiB
`MeetInstruct-0.6B-v1.5-Q3_K_S.gguf`	371.9 MiB
`MeetInstruct-0.6B-v1.5-Q2_K.gguf`	331.2 MiB

Recommended general-purpose quantization: MeetInstruct-0.6B-v1.5-Q4_K_M.gguf.

llama.cpp

Run the model with:

llama-cli -m MeetInstruct-0.6B-v1.5-Q4_K_M.gguf -cnv

Context support depends on the underlying checkpoint and available memory. The v1.5 16K checkpoint was trained with examples between approximately 10,000 and 15,900 tokens, but long-context reliability is not guaranteed.

Quantizations

Generated locally using the current llama.cpp quantizer.

Successful quantizations: Q8_0, Q6_K, Q5_K_M, Q5_K_S, Q4_K_M, Q4_K_S, Q3_K_L, Q3_K_M, Q3_K_S, Q2_K.

Downloads last month: 249

GGUF

Model size

0.8B params

Architecture

qwen3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Ma7ee7/MeetInstruct-0.6B-v1.5-GGUF

Base model

Ma7ee7/MeetInstruct-0.6B-v1.5

Quantized

(2)

this model