Gemma 2 27B Instruct

Running Gemma 2 27B Instruct locally

At Q4_K_M and 4K of context, Gemma 2 27B Instruct needs about 18.8 GB — 15.7 GB of weights, 1.44 GB of KV cache and a 1.7 GB activation buffer. The smallest card in this index that clears that comfortably is the RTX 4090 at 24 GB, and 29 of the 63 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 10.06 GB, taking the total to 29.9 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 8K; holding all of it at Q4_K_M would need about 20 GB.

Which build to download

This index tracks 2 formats for it — GGUF, AWQ — across 3 levels. Q5_K_M carries the lowest published perplexity loss at 1.3%. The fastest level measured here is AWQ INT4 at 58 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 2 27B Instruct need?

About 18.8 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 29.9 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 2 27B Instruct run on a 24GB GPU?

Yes — at Q4_K_M and 4K context it needs about 18.8 GB, which leaves 5.2 GB spare on a RTX 4090. That is the smallest card in this index that clears it comfortably; 29 of 63 do.

Which quantization of Gemma 2 27B Instruct should I use?

Q5_K_M has the lowest published quality loss (1.3%), and Q4_K_M is the level most people run. All 3 levels in the index are Q4_K_M, Q5_K_M, AWQ INT4.