Language

Phi-4 Mini 3.8B

Compact Phi-4 Mini with 128K context

MITSource verified

Specification

Model ID

phi4-mini

Family

phi

Modality

Language

Parameters

3.8B

Context

128,000 tokens

Quantization

Q4_K_M

Weights

2.3 GB

Minimum RAM

3 GB

Source

Weights and provenance.

Repository

unsloth/Phi-4-mini-instruct-GGUF

Registry license

MIT

Source license

mit

Access

Open — weights fetch without accepting additional terms.

Serve it

# Pull the weights onto a node
tenzro model download phi4-mini

# Serve it
tenzro model serve phi4-mini

# Or query the registry entry over JSON-RPC
curl https://rpc.tenzro.xyz \
  -X POST -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,
       "method":"tenzro_getModel",
       "params":[{"model_id":"phi4-mini"}]}'

Same family

Phi-4 14B

14B

Phi-4 Mini Reasoning 3.8B