Only with CPU offload

Gemma 3 27B at Q4_K_M needs 17.0 GB but only 14.4 GB is addressable, so about 17% of the layers would stream from system RAM at roughly 60 GB/s. Expect around 9.8 tokens per second — usable for batch work, painful for chat.

83% on GPU 8K context Q4_K_M · 15.4 GB Gemma Terms of Use Released Mar 2025 Vision

The 2025 single-GPU generalist with vision. Its Gemma-licence terms are the reason to prefer Gemma 4 now.

Hardware requirements What hardware do I need to run Gemma 3 27B? →

At Q4_K_M with an 8K context: a 24 GB GPU (RTX 4090) or a 32 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

Fits instead: Gemma 3 12B (8.3 GB) · Gemma 3 4B (3.3 GB)

The VRAM budget

weights 15.4 GB
Weights 15.4 GB KV cache @ 8K 1.03 GB Runtime overhead 0.6 GB Over budget 2.6 GB past 14.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 27.1 GB 28.7 GB — ~2.4 −0.1% ppl 14.3 GB over
Q6_K 20.9 GB 22.6 GB — ~3.9 −0.4% ppl 8.2 GB over
Q5_K_M 18.1 GB 19.7 GB — ~5.7 −0.8% ppl 5.3 GB over
Q4_K_M 15.4 GB 17.0 GB — ~9.8 −1.9% ppl 2.6 GB over
Q3_K_M 12.5 GB 14.1 GB 11K 35 −5.4% ppl Fits
Q2_K 10.7 GB 12.3 GB 34K 41 −15% ppl Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (1024 tokens, 1 global in 6), which is why its cache barely grows with context.

How to run it

terminal
$ llama-server \
    -hf google/gemma-3-27b-it:Q4_K_M \
    -c 8192 -ngl 51

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 15.4 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.
See all models for this rig Compare with another model

Related models on a GeForce RTX 4080

ModelTotalTok/s est.
Gemma 3 12B
12.2B · same family
Q4_K_M · 8.3 GB 63 Runs great
Gemma 3 4B
4.3B · same family
Q4_K_M · 3.3 GB 180 Runs great
Gemma 3 1B
1.0B · same family
Q4_K_M · 1.2 GB 772 Runs great
Qwen3.8 27B
27.8B · similar size
Q4_K_M · 16.7 GB ~11 CPU offload
Qwen3.6 27B
27.8B · similar size
Q4_K_M · 16.7 GB ~11 CPU offload
Gemma 4 26B-A4B
26.5B MoE · similar size
Q4_K_M · 16.0 GB ~36 CPU offload
Granite 4.1 30B
28.9B · similar size
Q4_K_M · 18.9 GB ~6.7 CPU offload

Every model against the GeForce RTX 4080 →

Gemma 3 27B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
17.0 GB ~3.2 CPU offload
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
17.0 GB ~4.6 CPU offload
M4 · 16 GB
10.7 GB usable · 120 GB/s
17.0 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
17.0 GB 40 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
17.0 GB 38 Runs great
M4 · 32 GB
24.0 GB usable · 120 GB/s
17.0 GB 4.4 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
17.0 GB 15 Runs great

All 114 devices, by tier →