Instructions to use prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-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 prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16

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 prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16

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 prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16

Use Docker

docker model run hf.co/prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16

Llama new
LM Studio
Jan

vLLM

How to use prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-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": "prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16

SGLang

How to use prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16
```
Unsloth Desktop

How to use prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16

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": "prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16
```

Lemonade

How to use prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16

Run and chat with the model

lemonade run user.flint-MXFP4_MOE-40B-A2.5B-GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-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 prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16

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 prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16

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 "prithivMLmods/flint-MXFP4_MOE-40B-A2.5B-GGUF:BF16" \
  --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"

flint-MXFP4_MOE-40B-A2.5B-GGUF

Recursive Flint (40B-A2.5B) is an open-weight, Apache 2.0-licensed decoder-only mixture-of-experts (MoE) language model developed from scratch by Recursive (Recursive Superintelligence, Inc.) specifically for coding agents. Built with 39.8 billion total parameters and approximately 2.5 billion active parameters per token across 49 layers (2 dense and 47 MoE layers using a mix of 513-token sliding-window and full attention), the model supports a 262,144-token context window, extended reasoning, and multi-turn OpenAI-compatible tool use. Purpose-built to investigate codebases, fix bugs, implement features, and write tests, Flint achieves 89.7% on SWE-bench Pro v2, 74.2% on SWE-bench Verified, and 54.9% on Terminal-Bench 2.1. While the main repository provides the BF16 checkpoint (~80 GB) and an SGLang serving kit tailored for single NVIDIA B300 or H200 GPUs, separate quantized variants (such as NVFP4, MLX INT4, and GGUF) are also available for local execution on NVIDIA hardware and Apple Silicon.

Model Files

File Name	Quant Type	File Size	File Link	Description
flint.BF16.gguf	BF16	79.6 GB	Link	Full BF16 weights. Highest quality, largest file size.
flint.MXFP4_MOE.gguf	MXFP4_MOE	22.2 GB	Link	Mixed precision / MoE optimized quantization. Highly efficient size for massive models, recommended if your inference engine supports it.
flint.Q5_K_M.gguf	Q5_K_M	28.3 GB	Link	High quality, recommended.

MXFP4-MOE Test Run

Tested flint.MXFP4_MOE on an NVIDIA RTX PRO 6000 Blackwell Server Edition GPU with 96 GB of VRAM, using llama-cli with full GPU offloading.

Performance Metrics

Metric	Value
Prompt Processing Speed	262.8 tokens/s
Generation Speed	164.9 tokens/s
Total Wall Time	14.231 seconds
Context Length	8,192 tokens
KV Cache (K)	`q8_0`
GPU	NVIDIA RTX PRO 6000 Blackwell Server Edition
GPU VRAM Capacity	96 GB
Peak GPU VRAM Usage	21.35 GiB
Peak GPU Utilization	92%
GPU Layers Offloaded	99 (`-ngl 99`)
Maximum Generation Tokens	16,384
Random Seed	42

Run Inference

./build/bin/llama-cli \
  -m /path/to/models/flint.MXFP4_MOE.gguf \
  -ngl 99 \
  -c 8192 \
  --cache-type-k q8_0 \
  --seed 42 \
  -n 16384 \
  -st \
  -p "Your prompt here"

Notes

Full GPU offloading: -ngl 99 requests offloading up to 99 model layers to the GPU. Actual offloading depends on the model architecture and the number of layers available.
KV cache: --cache-type-k q8_0 configures the K cache to use the q8_0 quantization format.
Context length: -c 8192 sets the context size to 8,192 tokens.
Generation length: -n 16384 sets the maximum number of tokens to generate.
Random seed: --seed 42 sets the random seed for reproducibility.

Performance results reflect this specific hardware and inference configuration. Actual throughput may vary depending on the prompt, model, software build, and runtime settings.