LocalClaw/LLM/Phi-4 (14B)
Open-weight local LLM

Phi-4 (14B)

Catalogue summary: Microsoft's full Phi-4. Compact powerhouse with exceptional reasoning and coding for its size. MIT licensed.

Repository editorial metadata; verify comparative claims in the linked upstream material.

16 GB catalogue minimum16 GB RAMQ6_KCoding assistant
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
14B
Minimum RAM
16 GB
Model size
12 GB
Quantization
Q6_K

Can Phi-4 (14B) run locally?

Phi-4 (14B) has a catalogue minimum of 16 GB RAM with Q6_K. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use phi-4-instruct as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Public GGUF repository (verified 2026-09-07): microsoft/phi-4-ggufUpstream releasePaper or model cardLicence text
chatcodepowerreasoning

Install path

01
Check RAM fitMinimum 16 GB RAM. Start with the Q6_K quant.
02
Load the modelSearch phi-4-instruct in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: phi
  • Parameters: 14B
  • Recommended quantization: Q6_K
  • Catalogue minimum RAM: 16 GB
  • Catalogue model size: 12 GB
  • Tags: chat, code, power, reasoning

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • power
  • reasoning

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
7
quality
8
coding
9
reasoning
8

Technical notes

Developer
Microsoft Research
License
MIT
Context window
16,384 tokens
Architecture
Transformer decoder-only

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Starter desktopMac mini M4 16GBPortable fitMacBook Air M4 16GBBest 16GB models16GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Phi-3.5 MoE Instruct 42B (6.6B active, MoE)Phi-3 Medium (14B) 14BPhi-4 Reasoning (14B) 14BPhi-3 (3.8B) 3.8BPhi-4 Mini (3.8B) 3.8BPhi-3.5 (3.8B) 3.8BPhi-4 Mini Reasoning (3.8B) 3.8BGemma 4 12B 12B

Where to go next