Gemma 3 27B IT

27B

Google Gemma 3

Gemma 3 large instruct with long context and multimodal support. Q4 ~16GB — dual-GPU or 24GB card with short ctx.

351.8K HF downloads2025 likesgoogle/gemma-3-27b-it· stats from 9/13/2026
Consumer GPUPro GPU

131K

Max Context

3

Quant Variants

GGUF Q4_K_M

Best Quality

97.2%

Accuracy Retained

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = site benchmarks · Estimated = formula · Community = public reports

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ4_K_M4.8516.2 GB2.8%48 tok/sCommunity
CalcHF
GGUFQ3_K_M3.8713.0 GB5.5%55 tok/sEstimated
CalcHF
AWQINT4414.5 GB3.8%62 tok/sEstimated
CalcHF

Similar models

Compare with Gemma 3

Running Gemma 3 27B IT locally

At Q4_K_M and 4K of context, Gemma 3 27B IT needs about 19.5 GB — 15.8 GB of weights, 1.94 GB of KV cache and a 1.8 GB activation buffer. The smallest card in this index that clears that comfortably is the RTX 4090 at 24 GB, and 29 of the 61 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 13.56 GB, taking the total to 34.4 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 86 GB.

Which build to download

This index tracks 2 formats for it — GGUF, AWQ — across 3 levels. Q4_K_M carries the lowest published perplexity loss at 2.8%. The fastest level measured here is AWQ INT4 at 62 tok/s on an RTX 4090, batch 1. 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 and CUDA only.

Common questions

How much VRAM does Gemma 3 27B IT need?
About 19.5 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 34.4 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 Gemma 3 27B IT run on a 24GB GPU?
Yes — at Q4_K_M and 4K context it needs about 19.5 GB, which leaves 4.5 GB spare on a RTX 4090. That is the smallest card in this index that clears it comfortably; 29 of 61 do.
Which quantization of Gemma 3 27B IT should I use?
Q4_K_M has the lowest published quality loss (2.8%), and Q4_K_M is the level most people run. All 3 levels in the index are Q4_K_M, Q3_K_M, 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.

Tight but possible
Radeon RX 7900 XT20GB
Ships in
GGUFAWQ
Compared here
GGUF vs AWQ

This page's figures change when the model or the runtime does.Last updated 2026-09-13 RSS → /feed.xml