Phi-3 Medium 14B Instruct
14BMicrosoft Phi
Microsoft's mid-size Phi-3. Excellent quality-per-GB on 16GB cards.
131K
Max Context
3
Quant Variants
GGUF Q6_K
Best Quality
99.2%
Accuracy Retained
Quantization Variants
Per-quant VRAM, quality loss, and inference speed on RTX 4090
Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports
Similar models
Compare with Phi-4 14BPhi-4 14B
Microsoft Phi
Microsoft Phi-4 dense 14B — strong reasoning for size. Q4 ~9GB fits 12GB cards with moderate context.
Phi-4 Mini Instruct
Microsoft Phi
Latest Phi mini with improved math and code. Strong 4B-class performer.
Phi-3.5 Mini Instruct
Microsoft Phi
Microsoft's tiny powerhouse. Best 4B model for on-device deployment.
Qwen2.5 14B Instruct
Alibaba Qwen2.5
The sweet spot between performance and resource usage. 16GB VRAM with Q4.
Running Phi-3 Medium 14B Instruct locally
At Q4_K_M and 4K of context, Phi-3 Medium 14B Instruct needs about 9.7 GB — 8.1 GB of weights, 0.78 GB of KV cache and a 0.9 GB activation buffer. The smallest cards in this index that clear that comfortably are 12 GB ones — 10 of them, from the RTX 3060 12G up — and 65 of the 78 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.
What longer context costs
Going from 4K to 32K adds about 5.47 GB, taking the total to 15.7 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 128K; holding all of it at Q4_K_M would need about 36 GB.
Which build to download
This index tracks 2 formats for it — GGUF, AWQ — across 3 levels. Q6_K carries the lowest published perplexity loss at 0.8%. The fastest level listed is AWQ INT4 at about 135 tok/s on an RTX 4090, batch 1 — an estimate, not a run on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving.
Common questions
- How much VRAM does Phi-3 Medium 14B Instruct need?
- About 9.7 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 15.7 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
- Will Phi-3 Medium 14B Instruct run on a 12GB GPU?
- Yes — at Q4_K_M and 4K context it needs about 9.7 GB, which leaves 2.3 GB spare on a RTX 3060 12G, or on any of the other 12 GB cards here (10 in all). That is the smallest size in this index that clears it comfortably; 65 of 78 do.
- Which quantization of Phi-3 Medium 14B Instruct should I use?
- Q6_K has the lowest published quality loss (0.8%), and Q4_K_M is the level most people run. All 3 levels in the index are Q4_K_M, Q6_K, AWQ INT4.
Where this model fits
Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.
- Runs comfortably on
- RTX 3060 12G12GB · +2.3Radeon RX 6700 XT12GB · +2.3Radeon RX 7700 XT12GB · +2.3Arc B580 12G12GB · +2.3RTX 4070 Ti12GB · +2.3
- Tight but possible
- Arc B570 10G10GBRTX 3080 10G10GB
- Just misses
- RTX 4060+1.7GB overRTX 4060 Ti 8G+1.7GB over
- Compared here
- GGUF vs AWQ
- Try it yourself
- Size it in the calculatorGenerate the run command
How to actually run this
Deployment guides for this model and this class of hardware.
This page's figures change when the model or the runtime does.Last updated 2026-10-20 RSS → /feed.xml