Instructions to use positron-ai/microsoft_phi-4-ingest-best-gptq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use positron-ai/microsoft_phi-4-ingest-best-gptq with Transformers:

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

pipe = pipeline("text-generation", model="positron-ai/microsoft_phi-4-ingest-best-gptq")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("positron-ai/microsoft_phi-4-ingest-best-gptq")
model = AutoModelForCausalLM.from_pretrained("positron-ai/microsoft_phi-4-ingest-best-gptq", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use positron-ai/microsoft_phi-4-ingest-best-gptq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "positron-ai/microsoft_phi-4-ingest-best-gptq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "positron-ai/microsoft_phi-4-ingest-best-gptq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/positron-ai/microsoft_phi-4-ingest-best-gptq

SGLang

How to use positron-ai/microsoft_phi-4-ingest-best-gptq 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 "positron-ai/microsoft_phi-4-ingest-best-gptq" \
    --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": "positron-ai/microsoft_phi-4-ingest-best-gptq",
		"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 "positron-ai/microsoft_phi-4-ingest-best-gptq" \
        --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": "positron-ai/microsoft_phi-4-ingest-best-gptq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use positron-ai/microsoft_phi-4-ingest-best-gptq with Docker Model Runner:
```
docker model run hf.co/positron-ai/microsoft_phi-4-ingest-best-gptq
```

Positron AI Quantized Build

This repository contains a Positron AI quantized build of microsoft/phi-4 for tron inference on Positron FPGA-serving infrastructure.

Recommended Use

Use this artifact when you need a GPTQ 4-bit build of microsoft/phi-4 optimized for Positron's tron runtime. This build targets Positron's ingest-serving path, where runtime fidelity and FPGA deployability are prioritized over general-purpose GPU portability.

For general-purpose GPU inference, compare against the original model and other quantized formats before deployment.

Artifact Summary

Field	Value
Base model	microsoft/phi-4
Published artifact	microsoft_phi-4-ingest-best-gptq
Quantization method	GPTQ
Quantization format	gptq
Source precision	n/a
Target runtime	tron
Hardware target	FPGA
Release date	2026-06-30
License	mit

Quantization Details

Field	Value
Weight precision	4-bit
Activation precision	not quantized
Bits	4
Group size	64
Symmetric quantization	true
Activation ordering / desc_act	false
Damp percent	0.05
Calibration dataset	Universal mixed-domain set
Calibration samples	256
Calibration sequence length	4096
MoE experts per token	n/a
Quantization toolchain	GPTQModel 5.8.0, transformers 4.57.6, torch 2.9.1, CUDA 12.8

Validation Results

Metric	Result	Reference	Notes
Mean KL-divergence	0.0183	microsoft/phi-4	Mean across the prompt suite
P95 KL-divergence	0.0753	microsoft/phi-4	Mean of per-prompt 95th-percentile token KL-divergence
Top-1 agreement	0.9523	microsoft/phi-4	Greedy top-1 token agreement
Perplexity / NLL delta	+1.7%	microsoft/phi-4	Same prompt suite as KL-divergence
MMLU mean	pending	n/a	Evaluation pending

KL-divergence measures token-distribution drift between this quantized artifact and the BF16 reference model; lower values indicate closer agreement. It was computed on Positron's tron FPGA-serving path, so treat it as a runtime-specific drift measurement rather than a GPU benchmark.

Evaluation Methodology

Field	Value
Evaluation date	2026-06-30
Evaluation suite	Positron mixed-domain prompt suite
Number of prompts	12
Runtime	tron
Device	FPGA
Pass criteria	Measurement only (no fixed KL-divergence threshold)

Known Limitations

KL-divergence was measured on a 12-prompt Positron validation suite; treat it as a runtime validation signal, not a broad benchmark.
Results are specific to the Positron tron FPGA-serving path and may differ from GPU-native inference.
MMLU evaluation is pending; results will be added when available.

Provenance

This artifact was produced by Positron AI from microsoft/phi-4. The original model license and usage restrictions continue to apply.

Downloads last month: 19

Safetensors

Model size

15B params

Tensor type

BF16

I32

Model tree for positron-ai/microsoft_phi-4-ingest-best-gptq

Base model

microsoft/phi-4

Quantized

(167)

this model