CO

codegemma-7b-it

CodegemmaGGUF by RichardErkhovUpdated 2024-04-14
Download on Hugging Face
Parameters8.54B
Context8K
Layers28
Architecturegemma
Smallest quant3.5 GB
Quick answer

codegemma-7b-it needs about 9.6 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 3.5 GB (Q2_K) to 7.0 GB (Q6_K).

codegemma-7b-it is a 8.54B-parameter Codegemma model in GGUF format, quantized by RichardErkhov. Its trained context length is 8K tokens. The repository has 21 quant files, from 3.5 GB (Q2_K) to 7.0 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.5 GB 7.7 GB
Tight Get file →
IQ3_XS3.8 GB 8.1 GB
Too big Get file →
IQ3_S4.0 GB 8.2 GB
Too big Get file →
Q3_K_S4.0 GB 8.2 GB
Too big Get file →
IQ3_M4.1 GB 8.4 GB
Too big Get file →
Q3_K4.4 GB 8.6 GB
Too big Get file →
Q3_K_M4.4 GB 8.6 GB
Too big Get file →
Q3_K_L4.7 GB 9.0 GB
Too big Get file →
IQ4_XS4.8 GB 9.1 GB
Too big Get file →
Q4_05.0 GB 9.3 GB
Too big Get file →
IQ4_NL5.0 GB 9.3 GB
Too big Get file →
Q4_K_S5.0 GB 9.3 GB
Too big Get file →
Q4_K5.3 GB 9.6 GB
Too big Get file →
Q4_K_M5.3 GB 9.6 GB
Too big Get file →
Q4_15.5 GB 9.8 GB
Too big Get file →
Q5_06.0 GB 10.2 GB
Too big Get file →
Q5_K_S6.0 GB 10.2 GB
Too big Get file →
Q5_K6.1 GB 10.4 GB
Too big Get file →
Q5_K_M6.1 GB 10.4 GB
Too big Get file →
Q5_16.5 GB 10.7 GB
Too big Get file →
Q6_K7.0 GB 11.3 GB
Too big Get file →

What GPU do you need for codegemma-7b-it?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q2_K (3.5 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.0 GB file, about 11.3 GB in use).

Which codegemma-7b-it quant should you choose?

Q4_K_M is the usual starting point for codegemma-7b-it: it balances file size and quality well. Here it is a 5.3 GB file.

If memory is tight, the smallest file is Q2_K at 3.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma
Parameters8.54B
Layers28
Trained context8,192 tokens
KV cache (fp16)448 KB per token

Source

Quantized byRichardErkhov
FamilyCodegemma
Downloads (HF)234
Last updated2024-04-14

Frequently asked questions about codegemma-7b-it

How much VRAM does codegemma-7b-it need?

About 9.6 GB at Q4_K_M with an 8K context window. That is the 5.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run codegemma-7b-it on an 8 GB GPU?

Yes, with Q2_K: the 3.5 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of codegemma-7b-it GGUF?

It depends on the quant: Q2_K is 3.5 GB, IQ3_XS is 3.8 GB, IQ3_S is 4.0 GB, Q3_K_S is 4.0 GB, IQ3_M is 4.1 GB, Q3_K is 4.4 GB and 15 more.

What context length does codegemma-7b-it support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.8 GB at 8K and 3.8 GB at 8K.

Where can I download codegemma-7b-it GGUF?

The files are on Hugging Face in the RichardErkhov/google_-_codegemma-7b-it-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Codegemma models

All Codegemma →

Other small models

All small models →