Gemma 3n E4B IT vs Gemma 4 E4B IT OBLITERATED
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Gemma 3n E4B IT | Gemma 4 E4B IT OBLITERATED | |
|---|---|---|
| Parameters | 7.8B | 8.0B |
| Context | — | 131K |
| Architecture | — | Gemma4ForConditionalGeneration |
| License | Gemma Terms | Apache 2.0 |
| Downloads | 19.9K | 329.8K |
| Released | — | Apr 2026 |
VRAM by Quantization: Gemma 3n E4B IT vs Gemma 4 E4B IT OBLITERATED
| Quantization | Bits | Gemma 3n E4B IT VRAM | Gemma 4 E4B IT OBLITERATED VRAM |
|---|---|---|---|
| Q2_K | 3.40 | 3.7 GB | 3.9 GB |
| Q3_K_M | 3.90 | 4.2 GB | 4.4 GB |
| Q3_K_S | 3.50 | 3.8 GB | 4.0 GB |
| Q4_0 | 4.00 | 4.3 GB | — |
| Q4_K_M | 4.80 | 5.2 GB | 5.3 GB |
| Q5_K_M | 5.70 | 6.2 GB | 6.2 GB |
| Q6_K | 6.60 | 7.1 GB | 7.1 GB |
| Q8_0 | 8.00 | 8.6 GB | 8.5 GB |
Verdict
Gemma 3n E4B IT needs less VRAM at Q4_K_M (5.2 GB vs 5.3 GB), so it fits on smaller GPUs. Gemma 4 E4B IT OBLITERATED is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, Gemma 3n E4B IT or Gemma 4 E4B IT OBLITERATED?
At Q4_K_M, Gemma 3n E4B IT needs 5.2 GB and Gemma 4 E4B IT OBLITERATED needs 5.3 GB, so Gemma 3n E4B IT is the lighter option to run locally.
- What is the difference between Gemma 3n E4B IT and Gemma 4 E4B IT OBLITERATED?
Gemma 3n E4B IT is a 7.8B model from Google (Gemma family), while Gemma 4 E4B IT OBLITERATED is a 8.0B model from OBLITERATUS (Gemma family). Compare their VRAM requirements above to see which fits your GPU or Mac.