Which needs less VRAM, Gemma 2 Mitra E or Codegemma 2B?

At BF16, Gemma 2 Mitra E needs 19.4 GB and Codegemma 2B needs 5.5 GB, so Codegemma 2B is the lighter option to run locally.

What is the difference between Gemma 2 Mitra E and Codegemma 2B?

Gemma 2 Mitra E is a 9.2B model from buddhist-nlp (Gemma 2 family), while Codegemma 2B is a 2.5B model from Google (Gemma 2 family). Compare their VRAM requirements above to see which fits your GPU or Mac.

Gemma 2 Mitra E vs Codegemma 2B

Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.

Gemma 2 Mitra E

buddhist-nlp · 9.2B

Chat

Codegemma 2B

Google · 2.5B

ChatCode

Specifications

	Gemma 2 Mitra E	Codegemma 2B
Parameters	9.2B	2.5B
Context	8K	—
Architecture	Gemma2ForCausalLM	—
License	—	Gemma Terms
Downloads	179	5.8K
Released	Mar 2026	Aug 2024

VRAM by Quantization: Gemma 2 Mitra E vs Codegemma 2B

Quantization	Bits	Gemma 2 Mitra E VRAM	Codegemma 2B VRAM
BF16	16.00	19.4 GB	5.5 GB

Verdict

Codegemma 2B needs less VRAM at BF16 (5.5 GB vs 19.4 GB), so it fits on smaller GPUs. Codegemma 2B is the more widely downloaded of the two.

Frequently Asked Questions

Which needs less VRAM, Gemma 2 Mitra E or Codegemma 2B?: At BF16, Gemma 2 Mitra E needs 19.4 GB and Codegemma 2B needs 5.5 GB, so Codegemma 2B is the lighter option to run locally.
What is the difference between Gemma 2 Mitra E and Codegemma 2B?: Gemma 2 Mitra E is a 9.2B model from buddhist-nlp (Gemma 2 family), while Codegemma 2B is a 2.5B model from Google (Gemma 2 family). Compare their VRAM requirements above to see which fits your GPU or Mac.