unsloth / image-text-to-text updated 2 weeks ago

gemma-4-26B-A4B-it-GGUF

Name: gemma-4-26B-A4B-it-GGUF
Author: unsloth

Jun 9 Update: Added MTP support. See our MTP Guide. Apr 11 Update: Re-download for Google's latest chat template and llama.cpp fixes. Gemma 4 can now be run and fine-tuned in Unsloth Studio. Read our guide. See all versions of Gemma 4 (GGUF, 16-bit etc.) in our collection. Example of Gemma 4 E4B (4-bit GGUF) running in Unsloth Studio with tool-calling:

Params

—

Context

—

Downloads 30d

1.4 M

Likes

1,029

Commercial use: allowed apache-2.0 Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 10 days

1.5 M1.4 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

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

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
gemma-4-26B-A4B-it-UD-IQ2_XXS.gguf	IQ2_XXS	9.9 GB	11.4 GB	✅ Runs comfortably
gemma-4-26B-A4B-it-UD-IQ2_M.gguf	IQ2_M	10.0 GB	11.5 GB	✅ Runs comfortably
gemma-4-26B-A4B-it-UD-IQ3_S.gguf	IQ3_S	11.3 GB	12.9 GB	✅ Runs comfortably
gemma-4-26B-A4B-it-UD-IQ3_XXS.gguf	IQ3_XXS	11.4 GB	13.1 GB	✅ Runs comfortably
gemma-4-26B-A4B-it-UD-IQ4_NL.gguf	IQ4_NL	13.6 GB	15.5 GB	✅ Runs comfortably
gemma-4-26B-A4B-it-UD-IQ4_XS.gguf	IQ4_XS	13.6 GB	15.5 GB	✅ Runs comfortably
gemma-4-26B-A4B-it-Q8_0.gguf	Q8_0	26.9 GB	30.0 GB	❌ Won’t fit
gemma-4-26B-A4B-it-BF16-00001-of-00002.gguf	GGUF	49.9 GB	55.4 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Gemma4ForConditionalGeneration
Licence: apache-2.0
First seen on the Hub: 2026-04-01
Base model: gemma-4-26B-A4B-it
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Base gemma-4-26B-A4B-it google 11.7 M

Compare with

Qwen3.5-9B 12.4 M gemma-4-31B-it 11.9 M gemma-4-26B-A4B-it 11.7 M Qwen2.5-VL-7B-Instruct 9.3 M Qwen3.6-35B-A3B-FP8 8.9 M Qwen2.5-VL-3B-Instruct 8.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB