microsoft / text-generation Open weights Also via API updated 3 months ago

phi-4

Name: phi-4
Price: 0.07 USD
Author: microsoft

-------------------------------------------------------------------------------------------------------- Developers Microsoft Research Description phi-4 is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on hig...

Params

14.7 B

Context

16,384

Downloads 30d

276 K

Likes

2,341

Commercial use: allowed mit Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 103 K in the last 30 days (27.3%)

714 K276 K

Jul 28Sep 1Oct 6Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	29.3 GB	34.9 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 16K ctx	29.3 GB	37.1 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/phi-4
{
  "hf_id": "microsoft/phi-4",
  "params_b": 14.66,
  "context_length": 16384,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 275580,
  "vram_estimates": [
    { "quant": "bf16", "gb": 34.9 }
  ],
  "updated_at": "2026-07-28T18:04:14Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Use via API

via OpenRouter · USD per 1M tokens · synced 2026-11-10

$0.07

input / 1M

$0.14

output / 1M

—

cached input / 1M

$0.21

1M in + 1M out

Context window: 16,384 tokens
Max output: 14,745 tokens
Providers: 1
Cheapest provider: DeepInfra · $0.056 / $0.11
Best throughput: —
AA Intelligence / Coding / Agentic: — / — / —

✗ Tool calling ✗ Reasoning ✓ Structured outputs ✗ Image input ✗ File input ✗ Audio input ✗ Prompt caching

Specifications

Architecture: Phi3ForCausalLM
Parameters: 14.7 B
Tensor type: BF16
Context length: 16,384
Vocabulary: 100,352
Layers / heads: 40 / 40
Licence: mit
First seen on the Hub: 2024-12-11
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with any text-generation model

Popular comparisons

Qwen3-14B 12.9 M Qwen3-8B 6.8 M gpt-oss-20b 5.8 M Gemma-4-31B-IT-NVFP4 1.1 M Qwen2.5-Coder-14B-Instruct-AWQ 216 K granite-4.1-8b 192 K