Microsofttransformer

Phi-3.5 Mini Instruct (HF)

3.8B parameters • 2.3GB VRAM (Q4 estimate) • 8,192 context

Estimate · Q4_K_M · 4k context · batch 1. For dense 7B–70B this sits ~5–8% above the Q4_K_M GGUF file. Not peak runtime VRAM and not a measured bench.

Specifications

Parameters

3.8B

VRAM (Q4 est.)

2.3 GB

VRAM (FP16)

7.6 GB

Context Window

8,192

Architecture

transformer

License

Apache-2.0

Finding cloud alternatives...

Run Phi-3.5 Mini Instruct (HF) on GTX 1060 3GB

~2.3GB VRAM needed at Q4. GTX 1060 3GB has 3GB — buy hardware or rent cloud.

Amazon eBay Compare cloud prices

We may earn a commission from cloud and hardware partners at no extra cost to you.

Find the cheapest GPU that can run Phi-3.5 Mini Instruct (HF)

Compatibility Lab — check every GPU × quantization combination

→

Run Phi-3.5 Mini Instruct (HF) on...

GB200 NVL72✅ Fits Lambda Labs 1-Click Cluster (8x H100)✅ Fits Google Cloud A3 (8x H100)✅ Fits Azure ND H100 v5 (8x H100)✅ Fits AWS EC2 P5 Instance (8x H100)✅ Fits NVIDIA DGX H100✅ Fits

VRAM Calculator→GPU Comparison→Cloud GPU Pricing→

← Back to Models

Microsofttransformer

Phi-3.5 Mini Instruct (HF)

3.8B parameters • 2.3GB VRAM (Q4 estimate) • 8,192 context

Estimate · Q4_K_M · 4k context · batch 1. For dense 7B–70B this sits ~5–8% above the Q4_K_M GGUF file. Not peak runtime VRAM and not a measured bench.