Instructions to use prithivMLmods/amos-1-large-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/amos-1-large-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/amos-1-large-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/amos-1-large-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/amos-1-large-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/amos-1-large-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/amos-1-large-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 prithivMLmods/amos-1-large-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/amos-1-large-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 prithivMLmods/amos-1-large-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/amos-1-large-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 prithivMLmods/amos-1-large-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/amos-1-large-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/amos-1-large-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/amos-1-large-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/amos-1-large-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/amos-1-large-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/amos-1-large-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/amos-1-large-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/amos-1-large-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/amos-1-large-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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/amos-1-large-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/amos-1-large-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use prithivMLmods/amos-1-large-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/amos-1-large-GGUF:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/amos-1-large-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/amos-1-large-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": "prithivMLmods/amos-1-large-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/amos-1-large-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/amos-1-large-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/amos-1-large-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/amos-1-large-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.amos-1-large-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/amos-1-large-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/amos-1-large-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 prithivMLmods/amos-1-large-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/amos-1-large-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/amos-1-large-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 "prithivMLmods/amos-1-large-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"

amos-1-large-GGUF

Amos 1 large is the 27B model of the Amos 1 family, built on Qwen3.8-27B and described as the most capable of the four sizes, meant for the hardest calls: multi-step questions, long policies and trade-offs, and cases needing broad knowledge. Given a case as text, JSON or a photo plus a schema of typed questions, it answers every question in one forward pass with a probability for each allowed answer. It writes no text, so there is nothing to parse. Question types are yes/no (noul), pick one (choice, up to 255 options), rate (score), pick any (multi), quote (span) and point (region, with a photo). On the typed-decisions test split (2,000 decisions from four unseen workflows, zero-shot) it scores 76.1% accuracy, with the best KL (0.126) and Brier (0.069) of the models listed. Its accuracy is just under Decider 1 (76.8%, its makers' own figure) and Microsoft-Decision-1 (79.5%), and ahead of Perplexity Decider v1.1 (73.9%) and Cloudflare's Clef (72.5%). With per-question priors fitted on the benchmark's train split it reaches 80.25%, against Decider 1's 80.1%. On Decision Bench's 1,071 real records it scores 94.9%, ahead of Perplexity Decider v1.1 (94.5%), DeepSeek V4.1 Flash and Gemini 3.5 Flash (94.2%) and Jev 1.13 (93.8%). Its Decision Index 0.3 public score is 65.11, run with the board's own kit but without the private tests the board's ranking adds. It also scores 100.0 / 100.0 / 84.7 on JevBench public easy / standard / hard, 89.8% on ten public benchmarks, and 91.9% on RefCOCO for boxes centred on the named object. Median server time is 122 ms for a three-question request. It needs an 80 GB GPU and reads up to 131,072 tokens, and is available through a hosted keyless API or the self-hosted amos.serve package. The listed limits are that it is the slowest of the four sizes, long quotes such as a whole clause or address can come back cut short, and it is English only. It is released under Apache 2.0.

Amos 1 Large model available @ — https://huggingface.co/mukaddamzaid/amos-1-large/tree/main/model

MTP — Speculative Decoding: No

Model Files

File Name	Quant Type	File Size	File Link	Description
amos-1-large.BF16.gguf	BF16	53.8 GB	Link	Full BF16 weights. Highest quality, largest file size.
amos-1-large.Q3_K_L.gguf	Q3_K_L	14.3 GB	Link	Lower quality but usable, good for low RAM availability.
amos-1-large.Q4_K_M.gguf	Q4_K_M	16.5 GB	Link	Good quality, default size for most use cases, recommended.
amos-1-large.Q5_K_M.gguf	Q5_K_M	19.2 GB	Link	High quality, recommended.
amos-1-large.mmproj-bf16.gguf	mmproj-bf16	931 MB	Link	Multimodal projection file in BF16 format. Used for vision/language models.