Gemma 3 12B IT — Hardware Requirements & GPU Compatibility
Vision
Google Gemma 3 12B IT is a 12-billion parameter multimodal instruction-tuned model from Google's Gemma 3 series. It supports both text and image inputs, offering vision-language capabilities at a more accessible size point than the 27B variant. Gemma 3 12B IT runs on consumer GPUs with 12-16GB of VRAM in quantized formats, making it a practical choice for local multimodal inference without requiring top-tier hardware. Released under the Gemma license.
2.6M downloads
749 likesSpecifications
- Publisher
- Family
- Gemma 3
- Parameters
- 12.2B
- Context Length
- 32,768 tokens
- Release Date
- 2025-03-01
- License
- Gemma Terms
Get Started
HuggingFace
How Much VRAM Does Gemma 3 12B IT Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 5.7 GB | — | 5.18 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 5.9 GB | — | 5.33 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 6.5 GB | — | 5.94 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 6.7 GB | — | 6.09 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 8.0 GB | — | 7.31 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 9.6 GB | — | 8.68 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 11.1 GB | — | 10.05 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 13.4 GB | — | 12.19 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Gemma 3 12B IT?
Q4_K_M · 8.0 GBGemma 3 12B IT (Q4_K_M) requires 8.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 11+ GB is recommended. 39 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Gemma 3 12B IT?
Q4_K_M · 8.0 GB49 devices with unified memory can run Gemma 3 12B IT, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPad Pro M5 13" (16 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Gemma 3 12B IT
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Gemma 3 12B IT need?
Gemma 3 12B IT requires 8.0 GB of VRAM at Q4_K_M, or 26.8 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 12.2B × 4.8 bits ÷ 8 = 7.3 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M8.0 GB- Can NVIDIA GeForce RTX 4090 run Gemma 3 12B IT?
Yes, at Q8_0 (13.4 GB) or lower. Higher quantizations like BF16 (26.8 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Gemma 3 12B IT?
For Gemma 3 12B IT, Q4_K_M (8.0 GB) offers the best balance of quality and VRAM usage. Q5_K_S (9.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 3.7 GB.
VRAM requirement by quantization
IQ2_XXS3.7 GBQ3_K_S5.9 GBQ4_17.5 GBQ4_K_M ★8.0 GBQ5_K_S9.2 GBBF1626.8 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Gemma 3 12B IT on a Mac?
Gemma 3 12B IT requires at least 3.7 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Gemma 3 12B IT locally?
Yes — Gemma 3 12B IT can run locally on consumer hardware. At Q4_K_M quantization it needs 8.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Gemma 3 12B IT?
At Q4_K_M, Gemma 3 12B IT can reach ~547 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~82 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 ÷ 8.0 × 0.65 = ~647 tok/s
Estimated speed at Q4_K_M (8.0 GB)
~647 tok/s~82 tok/s~647 tok/s~547 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Gemma 3 12B IT?
At Q4_K_M, the download is about 7.31 GB. The full-precision BF16 version is 24.37 GB. The smallest option (IQ2_XXS) is 3.35 GB.
- Which GPUs can run Gemma 3 12B IT?
39 consumer GPUs can run Gemma 3 12B IT at Q4_K_M (8.0 GB). Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Gemma 3 12B IT?
52 devices with unified memory can run Gemma 3 12B IT at Q4_K_M (8.0 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.