Yes, just — 1.4 GB spare

Gemma 3 27B at Q4_K_M fits your RTX 4000 Ada entirely on the GPU at 8K context, at an estimated 14 tokens per second. Past 25K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully 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.

The VRAM budget

weights 15.4 GB
Weights 15.4 GB KV cache @ 8K 1.03 GB Runtime overhead 0.6 GB Free 1.4 GB of 18.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 27.1 GB 28.7 GB — ~2.8 −0.1% ppl 10.3 GB over
Q6_K 20.9 GB 22.6 GB — ~5.2 −0.4% ppl 4.2 GB over
Q5_K_M 18.1 GB 19.7 GB — ~8.8 −0.8% ppl 1.3 GB over
Q4_K_M 15.4 GB 17.0 GB 25K 14 −1.9% ppl Recommended
Q3_K_M 12.5 GB 14.1 GB 62K 17 −5.4% ppl Long context
Q2_K 10.7 GB 12.3 GB 85K 20 −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 99

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.
03Only 1.4 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 25K context.
See all models for this rig Compare with another model

Related models on an RTX 4000 Ada

ModelTotalTok/s est.
Gemma 3 12B
12.2B · same family
Q4_K_M · 8.3 GB 32 Runs great
Gemma 3 4B
4.3B · same family
Q4_K_M · 3.3 GB 90 Runs great
Gemma 3 1B
1.0B · same family
Q4_K_M · 1.2 GB 388 Runs great
Qwen3.8 27B
27.8B · similar size
Q4_K_M · 16.7 GB 14 Tight fit
Qwen3.6 27B
27.8B · similar size
Q4_K_M · 16.7 GB 14 Tight fit
Gemma 4 26B-A4B
26.5B MoE · similar size
Q4_K_M · 16.0 GB 39 Tight fit
Granite 4.1 30B
28.9B · similar size
Q4_K_M · 18.9 GB ~12 CPU offload

Every model against the RTX 4000 Ada →

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 →