Gemma 4 E2B
Gemma · Apache 2.0
Gemma 4's compact edge model. 5.1B total parameters with 2.3B effective via Per-Layer Embeddings. Supports text, image, audio, and video input. Runs on practically any dedicated GPU with 4 GB of VRAM or more. Successor to Gemma 3 4B with measurably better reasoning and multimodal capabilities. Apache 2.0 licensed.
- Parameters
- 5.1B
- Architecture
- Dense
- Context
- 128,000 tokens
- Released
- 2026-04-02
- Engines
- llama.cpp, ollama, vLLM, TGI
- Builder Tools
- Aider, Claude Code, Continue, Cursor, LM Studio, Ollama, Open WebUI, Windsurf
Parameters
5.1B
VRAM
4.5 GB
Context
125K
Formats
4
GPUs
43
Gemma 4 E2B (5.1B) requires 4.5 GB VRAM at recommended quality (Q6_K). At efficient quality (Q4_K_M), it fits in 4 GB VRAM, making it compatible with the NVIDIA RTX 4060 Laptop (40-60W). On NVIDIA Grace Blackwell Ultra GB300, expect approximately 500 tok/s at Q8_0. For the best experience, Starter AI Desktop ($582) is recommended.
Source: OwnRig methodology
4.5 GB
Q6_K
3.9 GB
125K tokens
Chat
VRAM Requirements
| Quality | Quantization | VRAM | File Size |
|---|---|---|---|
| full | Q8_0 | 5.5 GB | 4.97 GB |
| recommended | Q6_K | 4.5 GB | 3.9 GB |
| recommended | Q5_K_M | 4.2 GB | 3.66 GB |
| efficient | Q4_K_M | 4 GB | 3.46 GB |
Context Length Impact
KV cache VRAM at Q6_K quality. Longer context = more memory.
| Context | KV Cache | Total VRAM |
|---|---|---|
| 2K | 102 MB | 4.6 GB |
| 4K | 102 MB | 4.6 GB |
| 8K | 205 MB | 4.7 GB |
| 16K | 410 MB | 4.9 GB |
| 32K | 922 MB | 5.4 GB |
| 64K | 1.8 GB | 6.3 GB |
Compatible GPUs
43 devicesShowing 43 of 43 entries
Builder Context
Gemma 4 E2B is commonly used with Aider, Claude Code, Continue, Cursor, LM Studio, Ollama, Open WebUI, Windsurf. For an AI coding workflow, pair it with an embedding model like nomic-embed-text for local RAG.
Frequently Asked Questions
- How much VRAM does Gemma 4 E2B need?
- Gemma 4 E2B requires 4.5 GB VRAM at recommended quality (Q6_K). At lower quality settings, it can fit in as little as 4 GB.
- What is the best GPU for Gemma 4 E2B?
- The NVIDIA Grace Blackwell Ultra GB300 delivers the best performance for Gemma 4 E2B, achieving 500 tok/s at Q8_0 with an excellent rating.
- Can I run Gemma 4 E2B on an RTX 4060 Ti?
- Yes. On the NVIDIA GeForce RTX 4060 Ti 16GB, Gemma 4 E2B runs at 43 tok/s (Q8_0, good).
- What quantization should I use for Gemma 4 E2B?
- For the best quality, use Q6_K (4.5 GB VRAM). If your GPU has limited VRAM, Q4_K_M (4 GB) is the most efficient option with acceptable quality.
- Is Gemma 4 E2B good for coding?
- Yes. Gemma 4 E2B is used with Aider, Claude Code, Continue, Cursor, LM Studio, Ollama, Open WebUI, Windsurf for local AI coding. For the best coding experience, pair it with an embedding model for local RAG.
Related Guides
Tutorial
Running Gemma 4 locally: which GPU you actually need
Gemma 4 VRAM requirements for every variant: E2B, E4B, 26B-A4B, and 31B. Which GPUs can run each, what quantization to use, and the honest call on RTX 4060 vs RTX 4090.
Buying Guide
Mac Mini M4 for AI: which models run on 16 GB
Which AI models run on the Mac Mini M4 with 16 GB, 24 GB, or 48 GB of unified memory. Honest compatibility table, real quantization requirements, and the upgrade case for M4 Pro.
Data confidence: estimated. Source
VRAM requirements are calculated from model parameters and may vary by inference engine, context length, and batch size. Performance estimates are based on community benchmarks and should be verified for your specific configuration.Gemma is a trademark of its respective owner. OwnRig is not affiliated with or endorsed by the model creator.