// Phi · Text LLM
Phi-4-reasoning: VRAM & local deployment
14.7B parameters. About 12.0 GB at 4-bit and 34.4 GB at BF16 with one 8K-token request.
released 2025-04-09licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Microsoft · microsoft |
|---|---|
| Family / series | Phi · Phi-4-reasoning |
| Type | Text LLM (text-generation) |
| Parameters | 14.7B Source: counted from official safetensors weights |
| Context length | 32K tokens (32,768)max_position_embeddings in config.json |
| Architecture | 40 layers · GQA |
| Released weights | BF16 · 29.3 GBdownload |
| Licence | MIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-04-09 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Smallest GPU | Mac |
|---|---|---|---|---|---|
| BF16 / FP16 (original) | 29.3 GB | 34.4 GB | 39.5 GB | 2 × RTX 5090 (64GB) | Mac 64GB |
| FP8 / INT8 / Q8_0 | 15.6 GB | 19.3 GB | 24.3 GB | RTX 4090 24GB | Mac 36GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 8.9 GB | 12.0 GB | 17.0 GB | 16GB GPU | Mac 24GB |
KV cache per request: 8K 1.7 GB · 32K 6.7 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- llama.cpp — mentioned in the official model card
- Transformers — mentioned in the official model card
- Ollama — in the official Ollama library · phi4-reasoning
ollama run phi4-reasoning04Official repositories & quantised builds
2 official repo(s) from microsoft.
- Phi-4-reasoning main
- Phi-4-reasoning-onnx ONNX
05Other Phi models
All 18 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| Phi-4-reasoning-vision-15B | 15.1B | 12.3 GB | 2026-01-23 |
| Phi-mini-MoE-instruct | 7.6B / 2.4B | 6.6 GB | 2025-06-23 |
| Phi-tiny-MoE-instruct | 3.8B / 1.1B | 3.6 GB | 2025-06-23 |
| Phi-4-mini-flash-reasoning | 3.85B | 4.4 GB | 2025-06-19 |
| Phi-4-mini-reasoning | 3.84B | 4.1 GB | 2025-04-29 |
| Phi-4-reasoning-plus | 14.7B | 12.0 GB | 2025-04-17 |
| Phi-4-multimodal-instruct | 5.57B | 4.2 GB | 2025-02-24 |
| Phi-4-mini-instruct | 3.84B | 4.1 GB | 2025-02-19 |
06Sources
Data checked 2025-11-24. Parameters, context and licence are copied from the official repository; memory figures are our estimates.