browse/models/gemma-27b
LLMLocal inference

Gemma 2 27B

VRAM requirements to run Gemma 2 27B locally at each quantization level. Find the cheapest GPU that fits below.

Q4 VRAM
16 GB
Q8 VRAM
30 GB
FP16 VRAM
54 GB
Context window
8 k tokens
01  //  GPUs that can run Gemma 2 27B

Cheapest compatible hardware by quantization

Sorted cheapest first. All prices are approximate street prices.

Q4Q4_K_M (4-bit)
needs ≥16 GB VRAM
GPUVRAMPriceTier
16 GB$549AMD budgetBuy
16 GB$699Budget 16GBDetails
24 GB$749Best valueDetails
16 GB$749Best valueDetails
24 GB$849Used valueDetails
Q8Q8_0 (8-bit)
needs ≥30 GB VRAM
GPUVRAMPriceTier
32 GB$1,999EnthusiastBuy
48 GB$2,499Mac portableDetails
48 GB$2,499Used workstationDetails
128 GB$3,999ResearchersDetails
128 GB$4,699On-the-goDetails
FP16FP16 (full precision)
needs ≥54 GB VRAM
GPUVRAMPriceTier
128 GB$3,999ResearchersBuy
128 GB$4,699On-the-goDetails
96 GB$8,499Pro / studioDetails
512 GB$9,499Mac prosDetails
02  //  Frequently asked

Gemma 2 27B GPU questions

How much VRAM does Gemma 2 27B need?
Gemma 2 27B requires approximately 16GB VRAM at Q4 quantization, 30GB at Q8, or 54GB at full FP16 precision. Q4 is the most practical choice for consumer hardware.
What is the cheapest GPU to run Gemma 2 27B?
The cheapest single GPU that fits Gemma 2 27B at Q4 is the Radeon RX 9070 XT (16GB VRAM, ~$549). At Q4 you need at least 16GB.
Can I run Gemma 2 27B at FP16?
Yes. Gemma 2 27B at FP16 requires 54GB VRAM. Several workstation GPUs (48–96GB) can handle this on a single card.
What quantization is best for Gemma 2 27B?
Q4_K_M (16GB) offers the best hardware compatibility and still produces high-quality output. Q8_0 (30GB) is better for tasks needing higher accuracy at the cost of needing more VRAM. FP16 (54GB) is only practical on very high-end workstation hardware.
Browse all GPUs Compare GPUs