ChatCodingMulti-Purpose12.2B
Gemma 3 12B
Gemma · Gemma license
Google's efficient 12B model with strong chat and coding support.
- Parameters
- 12.2B
- Context
- 32,768 tokens
- Released
- 2025-03-12
- Engines
- llama.cpp, ollama, vLLM, TGI
- Builder Tools
- Cursor, Continue, Aider, Open WebUI, LM Studio
Gemma 3 12B (12.2B) requires 10.5 GB VRAM at recommended quality (Q6_K). At efficient quality (Q4_K_M), it fits in 7 GB VRAM, making it compatible with the NVIDIA GeForce RTX 3060 12GB. On NVIDIA GeForce RTX 4090, expect approximately 75 tok/s at Q5_K_M. For the best experience, Starter AI Desktop ($582) is recommended.
— OwnRig methodology, data updated 2026-03-15
VRAM Requirements
| Quality | Quantization | VRAM | File Size |
|---|---|---|---|
| full | Q8_0 | 13.5 GB | 12 GB |
| recommended | Q6_K | 10.5 GB | 9.2 GB |
| recommended | Q5_K_M | 8.8 GB | 7.5 GB |
| efficient | Q4_K_M | 7 GB | 6 GB |
| compressed | Q3_K_M | 5.7 GB | 4.8 GB |
Context Length Impact
KV cache VRAM at Q6_K quality. Longer context = more memory.
| Context | KV Cache | Total VRAM |
|---|---|---|
| 2K | 205 MB | 10.7 GB |
| 4K | 410 MB | 10.9 GB |
| 8K | 819 MB | 11.3 GB |
| 16K | 1.5 GB | 12 GB |
| 32K | 3.1 GB | 13.6 GB |
Compatible GPUs
Performance data for Gemma 3 12B across different hardware.
| Device | Quantization | Speed | Rating | Fits in VRAM |
|---|---|---|---|---|
| NVIDIA GeForce RTX 3060 12GB | Q4_K_M | 32 tok/s | Good | ✓ |
| NVIDIA GeForce RTX 4060 Ti 16GB | Q5_K_M | 42 tok/s | Good | ✓ |
| NVIDIA GeForce RTX 4090 | Q5_K_M | 75 tok/s | Excellent | ✓ |
| NVIDIA GeForce RTX 5080 | Q5_K_M | 72 tok/s | Excellent | ✓ |
| NVIDIA GeForce RTX 4060 8GB | Q3_K_M | 18 tok/s | Marginal | ✓ |
| NVIDIA GeForce RTX 4070 Ti 12GB | Q4_K_M | 32 tok/s | Good | ✓ |
| NVIDIA GeForce RTX 3080 10GB | Q3_K_M | 28 tok/s | Acceptable | ✓ |
| Apple M3 Pro (18GB Unified) | Q3_K_M | 5 tok/s | Marginal | ✓ |
Builder Context
Gemma 3 12B is commonly used with Cursor, Continue, Aider, Open WebUI, LM Studio. For an AI coding workflow, pair it with an embedding model like nomic-embed-text for local RAG.
Recommended Builds
Complete PC builds that can run Gemma 3 12B.
Frequently Asked Questions
- How much VRAM does Gemma 3 12B need?
- Gemma 3 12B requires 10.5 GB VRAM at recommended quality (Q6_K). At lower quality settings, it can fit in as little as 5.7 GB.
- What is the best GPU for Gemma 3 12B?
- The NVIDIA GeForce RTX 4090 delivers the best performance for Gemma 3 12B, achieving 75 tok/s at Q5_K_M with an excellent rating.
- Can I run Gemma 3 12B on an RTX 4060 Ti?
- Yes. On the NVIDIA GeForce RTX 4060 Ti 16GB, Gemma 3 12B runs at 42 tok/s (Q5_K_M, good).
- What quantization should I use for Gemma 3 12B?
- For the best quality, use Q6_K (10.5 GB VRAM). If your GPU has limited VRAM, Q3_K_M (5.7 GB) is the most efficient option with acceptable quality.
- Is Gemma 3 12B good for coding?
- Yes. Gemma 3 12B is used with Cursor, Continue, Aider, Open WebUI, LM Studio for local AI coding. For the best coding experience, pair it with an embedding model for local RAG.
Data confidence: estimated. Last updated: 2026-03-15. Source