Instructions to use ubergarm/MiniMax-M2.7-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ubergarm/MiniMax-M2.7-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ubergarm/MiniMax-M2.7-GGUF",
	filename="BROKEN-TEST-ONLY-DONT-DOWNLOAD-MiniMax-M2.7-iq1_s_q4_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/MiniMax-M2.7-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q
# Run inference directly in the terminal:
llama-cli -hf ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q
# Run inference directly in the terminal:
llama-cli -hf ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q

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/MiniMax-M2.7-GGUF:IQ1_S_Q
# Run inference directly in the terminal:
./llama-cli -hf ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q

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/MiniMax-M2.7-GGUF:IQ1_S_Q
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q

Use Docker

docker model run hf.co/ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q

LM Studio
Jan

vLLM

How to use ubergarm/MiniMax-M2.7-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ubergarm/MiniMax-M2.7-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/MiniMax-M2.7-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q

Ollama
How to use ubergarm/MiniMax-M2.7-GGUF with Ollama:
```
ollama run hf.co/ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q
```

Unsloth Studio

How to use ubergarm/MiniMax-M2.7-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/MiniMax-M2.7-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/MiniMax-M2.7-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/MiniMax-M2.7-GGUF to start chatting

How to use ubergarm/MiniMax-M2.7-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q

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/MiniMax-M2.7-GGUF:IQ1_S_Q"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ubergarm/MiniMax-M2.7-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q

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/MiniMax-M2.7-GGUF:IQ1_S_Q

Run Hermes

hermes

Docker Model Runner
How to use ubergarm/MiniMax-M2.7-GGUF with Docker Model Runner:
```
docker model run hf.co/ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q
```

Lemonade

How to use ubergarm/MiniMax-M2.7-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ubergarm/MiniMax-M2.7-GGUF:IQ1_S_Q

Run and chat with the model

lemonade run user.MiniMax-M2.7-GGUF-IQ1_S_Q

List all available models

lemonade list

Testing smol-IQ4_KSS

by shewin - opened Apr 14

Discussion

shewin

Apr 14

Tensor blk.61.ffn_down_exps.weight (size = 579.00 MiB) buffer type overriden to CUDA_Host

Allocating 105.31 GiB of pinned host memory, this may take a while.
Using pinned host memory improves PP performance by a significant margin.
But if it takes too long for your model and amount of patience, kill the process and run using

GGML_CUDA_NO_PINNED=1 your_command_goes_here
done allocating 105.31 GiB in 29232.6 ms

llm_load_tensors: offloading 62 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 63/63 layers to GPU
llm_load_tensors: CUDA_Host buffer size = 107837.70 MiB
llm_load_tensors: CUDA0 buffer size = 3441.36 MiB
....................................................................................................
~ggml_backend_cuda_context: have 0 graphs
llama_init_from_model: n_ctx = 180224
llama_init_from_model: n_batch = 4096
llama_init_from_model: n_ubatch = 4096
llama_init_from_model: flash_attn = 1
llama_init_from_model: attn_max_b = 4096
llama_init_from_model: fused_moe = 1
llama_init_from_model: grouped er = 1
llama_init_from_model: fused_up_gate = 1
llama_init_from_model: fused_mmad = 1
llama_init_from_model: rope_cache = 0
llama_init_from_model: graph_reuse = 1
llama_init_from_model: k_cache_hadam = 0
llama_init_from_model: v_cache_hadam = 0
llama_init_from_model: split_mode_graph_scheduling = 0
llama_init_from_model: reduce_type = f16
llama_init_from_model: sched_async = 0
llama_init_from_model: ser = -1, 0
llama_init_from_model: freq_base = 5000000.0
llama_init_from_model: freq_scale = 1
llama_kv_cache_init: CUDA0 KV buffer size = 23188.03 MiB
llama_init_from_model: KV self size = 23188.00 MiB, K (q8_0): 11594.00 MiB, V (q8_0): 11594.00 MiB
llama_init_from_model: CUDA_Host output buffer size = 0.76 MiB
llama_init_from_model: CUDA0 compute buffer size = 3222.00 MiB
llama_init_from_model: CUDA_Host compute buffer size = 1456.05 MiB
llama_init_from_model: graph nodes = 2361
llama_init_from_model: graph splits = 126
llama_init_from_model: enabling only_active_experts scheduling

main: n_kv_max = 180224, n_batch = 4096, n_ubatch = 4096, flash_attn = 1, n_gpu_layers = 99, n_threads = 101, n_threads_batch = 101

PP	TG	N_KV	T_PP s	S_PP t/s	T_TG s	S_TG t/s
4096	1024	0	2.826	1449.24	25.492	40.17
4096	1024	4096	2.881	1421.62	26.517	38.62
4096	1024	8192	3.006	1362.74	27.692	36.98
4096	1024	12288	3.126	1310.18	28.568	35.84
4096	1024	16384	3.250	1260.23	30.612	33.45

shewin

Apr 14

Speedy but results are worse than IQ5

Johngugu

Apr 15

Hello! could you please share your system specification? how much vram / ram? generation speed looks amazing! Thank you!

shewin

Apr 16

W790E Sage + QYFS + 512G + RTX5090

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment