Phi-3.5 Mini Instruct
3.8BMicrosoft Phi
Microsoft's tiny powerhouse. Best 4B model for on-device deployment.
131K
Max Context
3
Quant Variants
GGUF Q8_0
Best Quality
99.8%
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 MiniPhi-4 Mini Instruct
Microsoft Phi
Latest Phi mini with improved math and code. Strong 4B-class performer.
Phi-3 Medium 14B Instruct
Microsoft Phi
Microsoft's mid-size Phi-3. Excellent quality-per-GB on 16GB cards.
Phi-4 14B
Microsoft Phi
Microsoft Phi-4 dense 14B — strong reasoning for size. Q4 ~9GB fits 12GB cards with moderate context.
Llama 3.1 8B Instruct
Meta Llama 3.1
Meta's flagship 8B model with 128K context. Best-in-class for local deployment.
Running Phi-3.5 Mini Instruct locally
At Q4_K_M and 4K of context, Phi-3.5 Mini Instruct needs about 4.1 GB — 2.2 GB of weights, 1.50 GB of KV cache and a 0.4 GB activation buffer. The smallest cards in this index that clear that comfortably are 8 GB ones — 11 of them, from the Mac M1 8G up — and 78 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 10.50 GB, taking the total to 15.6 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 55 GB.
Which build to download
This index tracks 2 formats for it — GGUF, AWQ — across 3 levels. Q8_0 carries the lowest published perplexity loss at 0.2%. The fastest level listed is AWQ INT4 at about 385 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-3.5 Mini Instruct need?
- About 4.1 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 15.6 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-3.5 Mini Instruct run on a 8GB GPU?
- Yes — at Q4_K_M and 4K context it needs about 4.1 GB, which leaves 1.9 GB spare on a Mac M1 8G, or on any of the other 8 GB cards here (11 in all). That is the smallest size in this index that clears it comfortably; 78 of 78 do.
- Which quantization of Phi-3.5 Mini Instruct should I use?
- Q8_0 has the lowest published quality loss (0.2%), and Q4_K_M is the level most people run. All 3 levels in the index are Q4_K_M, Q8_0, 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
- Mac M1 8G8GB · +1.9Mac M3 8G8GB · +1.9RTX 40608GB · +3.9RTX 4060 Ti 8G8GB · +3.9Radeon RX 9060 XT 8G8GB · +3.9
- 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