CanItRun Logocanitrun.

Gemma 3 1B Instruct

Gemma 3 1B Instruct needs roughly 1.0 GB VRAM at Q4_K_M quantization (2.6 GB at FP16). 106 GPUs we track can run it fully in VRAM at 8k context.

106 GPUs run this natively · 1 with CPU offload

Google1B params32k contextGemmaCommercial use ok

Gemma 3 1B Instruct is a 1B parameter dense large language model developed by Google. Released in March 2025, it is a text-only model with a 32k context window, released under the Gemma license, allowing commercial use. Text-only; larger siblings support vision.

To run Gemma 3 1B Instruct locally, you need approximately 1.0 GB of VRAM at Q4_K_M quantization with 8k context. 106 of the GPUs we track can run it fully in VRAM, with a further 1 able to offload to system RAM. At Q4_K_M it needs just 1.0 GB, making it accessible even on mid-range 16 GB cards like RTX 4080 and RTX 4070 Ti Super. At Q8_K_M (1.5 GB), you get near-FP16 quality while still fitting on 8, 12, 16, 24, 48 and 80 GB GPUs. FP16 requires 2.6 GB, limiting it to 48 and 80 GB GPUs.

MMLU-Pro score of 14.7 indicates room exists for specialized or lightweight use cases. The license allows commercial use.

VRAM at each quantization

Assumes 8k context. KV cache grows linearly with context length.

QuantWeightsKV cacheTotal
FP324.0 GB0.33 GB4.8 GB
BF162.0 GB0.33 GB2.6 GB
FP162.0 GB0.33 GB2.6 GB
Q8_0rec1.0 GB0.33 GB1.5 GB
Q6_K0.8 GB0.33 GB1.3 GB
Q5_K_M0.6 GB0.33 GB1.1 GB
Q4_K_M0.6 GB0.33 GB1.0 GB
Q3_K_M0.4 GB0.33 GB0.8 GB
Q2_K0.3 GB0.33 GB0.7 GB
NVFP4cuda0.5 GB0.33 GB0.9 GB

KV cache shown at 8k context (FP16). NVFP4 requires a CUDA GPU. Enable TurboQuant in the calculator to see reduced KV cache estimates.

Benchmarks

MMLU-Pro
14.7

GPUs that run Gemma 3 1B Instruct natively (106)

Plus 1 GPUs that run it with CPU offload (slower)

Notes

Text-only; larger siblings support vision.

Hugging Face ↗Ollama ↗Released 2025-03-12

Compare Gemma 3 1B Instruct with other models

Frequently asked questions

What are the VRAM requirements for Gemma 3 1B Instruct?
Gemma 3 1B Instruct requires approximately 1.0 GB of VRAM at Q4_K_M quantization, 1.5 GB at Q8, and 2.6 GB at FP16. These numbers assume 8k context window; VRAM scales linearly with context length due to the KV cache.
How many parameters does Gemma 3 1B Instruct have?
Gemma 3 1B Instruct has 1 billion parameters.
How capable is Gemma 3 1B Instruct?
Gemma 3 1B Instruct has an MMLU-Pro score of 14.7, making it well-suited for lightweight tasks, prototyping, and resource-constrained environments.
Can Gemma 3 1B Instruct run on a 16 GB GPU?
Yes. Gemma 3 1B Instruct needs 1.0 GB at Q4_K_M, which fits in a 16 GB GPU like the RTX 4080 or RTX 4070 Ti Super.
What is the smallest quantization for Gemma 3 1B Instruct that fits in 24 GB of VRAM?
At FP32, Gemma 3 1B Instruct needs 4.8 GB — the highest-quality quantization that fits in 24 GB of VRAM.
What GPU do I need to run Gemma 3 1B Instruct locally?
A 16 GB GPU is enough. At Q4_K_M, Gemma 3 1B Instruct needs 1.0 GB VRAM. Good options: RTX 4080 (16 GB), RTX 4070 Ti Super (16 GB).