MaziyarPanahi / text-generation updated 1 year ago

gemma-3-4b-it-GGUF

MaziyarPanahi/gemma-3-4b-it-GGUF contains GGUF format model files for google/gemma-3-4b-it.

Params
Context
Downloads 30d
186 K
Likes
20
Licence: unknown Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 34 days
▲ 2 K in the last 30 days (1.3%)
187 K181 K
Aug 19Aug 30Sep 10Sep 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
gemma-3-4b-it.Q2_K.gguf Q2_K 1.7 GB 2.4 GB ✅ Runs comfortably
gemma-3-4b-it.Q3_K_S.gguf Q3_K_S 1.9 GB 2.6 GB ✅ Runs comfortably
gemma-3-4b-it.Q3_K_M.gguf Q3_K_M 2.1 GB 2.8 GB ✅ Runs comfortably
gemma-3-4b-it.Q3_K_L.gguf Q3_K_L 2.2 GB 3.0 GB ✅ Runs comfortably
gemma-3-4b-it.Q4_K_S.gguf Q4_K_S 2.4 GB 3.1 GB ✅ Runs comfortably
gemma-3-4b-it.Q4_K_M.gguf Q4_K_M 2.5 GB 3.2 GB ✅ Runs comfortably
gemma-3-4b-it.Q5_K_S.gguf Q5_K_S 2.8 GB 3.5 GB ✅ Runs comfortably
gemma-3-4b-it.Q5_K_M.gguf Q5_K_M 2.8 GB 3.6 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 · Q4_K_M
$ ollama run gemma-3-4b-it-gguf

# pin the quantization explicitly
$ ollama run gemma-3-4b-it-gguf-q4_k_m
est. VRAM 3.2 GBon RTX 4090 · 24 GBJSON API →

Specifications

First seen on the Hub
2025-03-12
Base model
gemma-3-4b-it
Training datasets
undisclosed
Added to our catalog
2026-08-19

Family

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

Compare with any text-generation model