Codegemma 7B vs Gemma 4 26B A4B IT

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

Codegemma 7B

Google · 8.5B

ChatCode
Gemma 4 26B A4B IT

Google · 26.5B

Vision

Specifications

Codegemma 7BGemma 4 26B A4B IT
Parameters8.5B26.5B
Context262K
ArchitectureGemma4ForConditionalGeneration
LicenseGemma TermsApache 2.0
Downloads2.0K12.3M
ReleasedAug 2024

VRAM by Quantization: Codegemma 7B vs Gemma 4 26B A4B IT

QuantizationBitsCodegemma 7B VRAMGemma 4 26B A4B IT VRAM
Q2_K3.404.0 GB11.9 GB
Q3_K_M3.904.6 GB13.6 GB
Q3_K_S3.504.1 GB12.3 GB
Q4_04.004.7 GB
Q4_K_M4.805.6 GB16.6 GB
Q5_K_M5.706.7 GB19.6 GB
Q6_K6.607.8 GB22.5 GB
Q8_08.009.4 GB27.2 GB

Verdict

Codegemma 7B needs less VRAM at Q4_K_M (5.6 GB vs 16.6 GB), so it fits on smaller GPUs. Gemma 4 26B A4B IT is the more widely downloaded of the two.

Frequently Asked Questions

Which needs less VRAM, Codegemma 7B or Gemma 4 26B A4B IT?

At Q4_K_M, Codegemma 7B needs 5.6 GB and Gemma 4 26B A4B IT needs 16.6 GB, so Codegemma 7B is the lighter option to run locally.

What is the difference between Codegemma 7B and Gemma 4 26B A4B IT?

Codegemma 7B is a 8.5B model from Google (Gemma family), while Gemma 4 26B A4B IT is a 26.5B model from Google (Gemma family). Compare their VRAM requirements above to see which fits your GPU or Mac.