ReasoningCodingChat14.7B
Phi-4 14B
Phi · MIT
Microsoft's efficient reasoning and coding model with strong performance per parameter.
- Parameters
- 14.7B
- Context
- 32,768 tokens
- Released
- 2025-02-26
- Engines
- llama.cpp, ollama, vLLM, TGI
- Builder Tools
- Cursor, Continue, Aider, Open WebUI, LM Studio
Phi-4 14B (14.7B) requires 12.6 GB VRAM at recommended quality (Q6_K). At efficient quality (Q4_K_M), it fits in 8.4 GB VRAM, making it compatible with the NVIDIA GeForce RTX 4060 8GB. On NVIDIA GeForce RTX 4090, expect approximately 58 tok/s at Q5_K_M. For the best experience, Budget Home AI Server ($1,162) is recommended.
— OwnRig methodology, data updated 2026-03-15
VRAM Requirements
| Quality | Quantization | VRAM | File Size |
|---|---|---|---|
| full | Q8_0 | 16.2 GB | 14.5 GB |
| recommended | Q6_K | 12.6 GB | 11 GB |
| recommended | Q5_K_M | 10.5 GB | 9 GB |
| efficient | Q4_K_M | 8.4 GB | 7.2 GB |
| compressed | Q3_K_M | 6.8 GB | 5.8 GB |
Context Length Impact
KV cache VRAM at Q6_K quality. Longer context = more memory.
| Context | KV Cache | Total VRAM |
|---|---|---|
| 2K | 205 MB | 12.8 GB |
| 4K | 512 MB | 13.1 GB |
| 8K | 1 GB | 13.6 GB |
| 16K | 1.9 GB | 14.5 GB |
| 32K | 3.8 GB | 16.4 GB |
Compatible GPUs
Performance data for Phi-4 14B across different hardware.
| Device | Quantization | Speed | Rating | Fits in VRAM |
|---|---|---|---|---|
| NVIDIA GeForce RTX 4060 Ti 16GB | Q4_K_M | 28 tok/s | Good | ✓ |
| NVIDIA GeForce RTX 4070 Ti Super | Q5_K_M | 42 tok/s | Good | ✓ |
| NVIDIA GeForce RTX 4090 | Q5_K_M | 58 tok/s | Excellent | ✓ |
| Apple M4 Max (36GB Unified) | Q5_K_M | 35 tok/s | Good | ✓ |
| NVIDIA GeForce RTX 5080 | Q4_K_M | 52 tok/s | Excellent | ✓ |
| Apple M4 Pro (48GB) | Q5_K_M | 35 tok/s | Good | ✓ |
| NVIDIA GeForce RTX 4080 Super | Q5_K_M | 48 tok/s | Excellent | ✓ |
| NVIDIA GeForce RTX 4060 8GB | Q3_K_M | 19 tok/s | Marginal | ✓ |
| NVIDIA GeForce RTX 4070 Ti 12GB | Q3_K_M | 34 tok/s | Acceptable | ✓ |
| NVIDIA GeForce RTX 3080 10GB | Q3_K_M | 26 tok/s | Acceptable | ✓ |
| Apple M3 Pro (18GB Unified) | Q3_K_M | 5 tok/s | Marginal | ✓ |
Builder Context
Phi-4 14B is commonly used with Cursor, Continue, Aider, Open WebUI, LM Studio. For an AI coding workflow, pair it with an embedding model like nomic-embed-text for local RAG.
Recommended Builds
Complete PC builds that can run Phi-4 14B.
Frequently Asked Questions
- How much VRAM does Phi-4 14B need?
- Phi-4 14B requires 12.6 GB VRAM at recommended quality (Q6_K). At lower quality settings, it can fit in as little as 6.8 GB.
- What is the best GPU for Phi-4 14B?
- The NVIDIA GeForce RTX 4090 delivers the best performance for Phi-4 14B, achieving 58 tok/s at Q5_K_M with an excellent rating.
- Can I run Phi-4 14B on an RTX 4060 Ti?
- Yes. On the NVIDIA GeForce RTX 4060 Ti 16GB, Phi-4 14B runs at 28 tok/s (Q4_K_M, good).
- What quantization should I use for Phi-4 14B?
- For the best quality, use Q6_K (12.6 GB VRAM). If your GPU has limited VRAM, Q3_K_M (6.8 GB) is the most efficient option with acceptable quality.
- Is Phi-4 14B good for coding?
- Yes. Phi-4 14B is used with Cursor, Continue, Aider, Open WebUI, LM Studio for local AI coding. For the best coding experience, pair it with an embedding model for local RAG.
Data confidence: estimated. Last updated: 2026-03-15. Source