MaziyarPanahi / text-generation updated 2 years ago

Phi-3.5-mini-instruct-GGUF

MaziyarPanahi/Phi-3.5-mini-instruct-GGUF contains GGUF format model files for microsoft/Phi-3.5-mini-instruct.

Params
Context
Downloads 30d
183 K
Likes
33
Licence: unknown Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 33 days
▲ 733 in the last 30 days (0.4%)
184 K180 K
Aug 20Aug 31Sep 11Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
Phi-3.5-mini-instruct.IQ1_S.gguf IQ1_S 0.8 GB 1.4 GB ✅ Runs comfortably
Phi-3.5-mini-instruct.IQ1_M.gguf IQ1_M 0.9 GB 1.5 GB ✅ Runs comfortably
Phi-3.5-mini-instruct.IQ2_XS.gguf IQ2_XS 1.2 GB 1.8 GB ✅ Runs comfortably
Phi-3.5-mini-instruct.Q2_K.gguf Q2_K 1.4 GB 2.1 GB ✅ Runs comfortably
Phi-3.5-mini-instruct.IQ3_XS.gguf IQ3_XS 1.6 GB 2.3 GB ✅ Runs comfortably
Phi-3.5-mini-instruct.Q3_K_M.gguf Q3_K_M 2.0 GB 2.7 GB ✅ Runs comfortably
Phi-3.5-mini-instruct.IQ4_XS.gguf IQ4_XS 2.1 GB 2.8 GB ✅ Runs comfortably
Phi-3.5-mini-instruct.Q3_K_L.gguf Q3_K_L 2.1 GB 2.8 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · ollama · IQ1_M
$ ollama run phi-3-5-mini-instruct-gguf

# pin the quantization explicitly
$ ollama run phi-3-5-mini-instruct-gguf-iq1_m
est. VRAM 1.5 GBon RTX 4090 · 24 GBJSON API →

Specifications

First seen on the Hub
2024-08-20
Base model
Phi-3.5-mini-instruct
Training datasets
undisclosed
Added to our catalog
2026-08-20

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any text-generation model