Gemma3 1B IT — Hardware Requirements & GPU Compatibility
Chat
Gemma3 1B IT is a 1B-parameter open language model from litert-community in the Gemma 3 family. At BF16 it needs about 2.20 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 32K)Best on 24 GB (BF16 · ~298 tok/s · 32K)Macs from 8 GB (BF16 · ~33 tok/s)
Gemma Terms
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Gemma3 1B IT
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve litert-community/Gemma3-1B-IT --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3060 12GB (8 GB headroom) · BF16
- Generation speed
- ~106 tok/s
- generation speed
- Cost per 1M output tokens
- $0.16
- per 1M output tokens
How Much VRAM Does Gemma3 1B IT Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.2 GB | 5.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~298 tok/s |
Selected BF16
Brain floating point 163.6GBat 16K context
- Weights
- 1.7 GB
- KV cache
- 1.6 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.4 GB free · ~298 tok/s
≥50 tok/s needs ≥169 GB/s · RTX 5090 ~530, RTX 3090 Ti ~298
Which Hardware Can Run Gemma3 1B IT?
BF16 · 2.2 GBGemma3 1B IT (BF16) requires 2.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Gemma3 1B IT, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.4 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~225Simulate output on RTX 3080RTX 2080 Ti~182Simulate output on RTX 2080 TiRTX 3070 Ti~180Simulate output on RTX 3070 TiM3*8 GB~33Simulate output on iMac 24" M3 (8 GB)Orin Nano~30Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~22Simulate output on iPhone 1720 GB
fits · 16.4 GB free · up to 32K ctx
1 GPU
RX 7900 XT~218Simulate output on RX 7900 XT32–40 GB
fits · 28.4 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~530Simulate output on RTX 5090M5 Max36 GB~146Simulate output on Mac Studio M5 Max (36 GB)M532 GB~49Simulate output on MacBook Air 13" M5 (32 GB)Orin~61Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~40Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Alternatives to Gemma3 1B IT
Gemma 3 family · 20 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| InternVL3 5 1BOpenGVLab | — | 2.2 GB | ~936 | same size |
| InternVL3 1BOpenGVLab | — | 2 GB | ~1057 | same size |
| InternVL2 1BOpenGVLab | — | 2 GB | ~1057 | same size |
| DiffuRefill 1BAsilarkness | — | 2.6 GB | ~252 | same size |
| Crowd V1Vxtzq | — | 3.7 GB | ~295 | same size |
| LLaMA3.1 8B Instruct DFlash UltraChatz-lab | — | 2.7 GB | ~269 | same size |
Specifications
- Publisher
- litert-community
- Family
- Gemma 3
- Parameters
- 1B
- Release Date
- 2025-03-11
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Gemma3 1B IT need?
Gemma3 1B IT requires 2.2 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 1B × 16 bits ÷ 8 = 2 GB
KV Cache + Overhead ≈ 0.2 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can I run Gemma3 1B IT on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Gemma3 1B IT. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 2.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run Gemma3 1B IT locally?
Yes — Gemma3 1B IT can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma3 1B IT?
At BF16, Gemma3 1B IT can reach ~2182 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~298 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 2.2 × 0.65 = ~2364 tok/s
Estimated speed at BF16 (2.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Gemma3 1B IT?
At BF16, the download is about 2.00 GB.
Which GPUs can run Gemma3 1B IT?
52 consumer GPUs can run Gemma3 1B IT at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Gemma3 1B IT?
163 devices with unified memory can run Gemma3 1B IT at BF16 (2.2 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.