Instructions to use QuantPasture/MiMo-V2.5-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 QuantPasture/MiMo-V2.5-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 QuantPasture/MiMo-V2.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf QuantPasture/MiMo-V2.5-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 QuantPasture/MiMo-V2.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf QuantPasture/MiMo-V2.5-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 QuantPasture/MiMo-V2.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantPasture/MiMo-V2.5-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 QuantPasture/MiMo-V2.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantPasture/MiMo-V2.5-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantPasture/MiMo-V2.5-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use QuantPasture/MiMo-V2.5-GGUF with Ollama:
```
ollama run hf.co/QuantPasture/MiMo-V2.5-GGUF:Q4_K_M
```
Unsloth Desktop

How to use QuantPasture/MiMo-V2.5-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf QuantPasture/MiMo-V2.5-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "QuantPasture/MiMo-V2.5-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use QuantPasture/MiMo-V2.5-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantPasture/MiMo-V2.5-GGUF:Q4_K_M
```

Lemonade

How to use QuantPasture/MiMo-V2.5-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantPasture/MiMo-V2.5-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiMo-V2.5-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use QuantPasture/MiMo-V2.5-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 QuantPasture/MiMo-V2.5-GGUF:Q4_K_M

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 QuantPasture/MiMo-V2.5-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use QuantPasture/MiMo-V2.5-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf QuantPasture/MiMo-V2.5-GGUF:Q4_K_M

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 "QuantPasture/MiMo-V2.5-GGUF:Q4_K_M" \
  --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"

Can you share the command you used to create the BF16 ggus?

#10

by tarruda - opened May 9

Discussion

tarruda

May 9

I downloaded the original safetensors but I'm getting an exception while converting to gguf:

INFO:gguf.gguf_writer:Writing the following files:
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00001-of-00015.gguf: n_tensors = 0, total_size = negligible - metadata only
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00002-of-00015.gguf: n_tensors = 375, total_size = 48.4G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00003-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00004-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00005-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00006-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00007-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00008-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00009-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00010-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00011-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00012-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00013-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00014-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00015-of-00015.gguf: n_tensors = 1, total_size = 4.3G
Shard (2/15):   1%|█▉                                                                                                                                            | 659M/48.4G [00:05<06:18, 126Mbyte/s/Users/thiago/.local/share/uv/python/cpython-3.12.7-macos-aarch64-none/lib/python3.12/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
  warnings.warn('resource_tracker: There appear to be %d '
./scripts/convert-to-gguf.sh: line 67: 33989 Bus error: 10

AesSedai

Aes Sedai's Quant Pasture org May 9

Sure, I didn't do anything special. Just:

source venv/bin/activate
python3 convert_hf_to_gguf.py $fp16_indir --outfile $ggml_outfile --outtype bf16

Bus error sounds weird :S

tarruda

May 12

Probably I got corrupted weights and will try re-downloading. Thanks!

tarruda changed discussion status to closed May 12

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