GE

frankenmerger gemma 4b instruct v0.2

GemmaGGUF by RichardErkhovUpdated 2024-10-04
Download on Hugging Face
Parameters4.05B
Context8K
Layers32
Architecturegemma
Smallest quant1.7 GB
Quick answer

frankenmerger gemma 4b instruct v0.2 needs about 3.3 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 1.7 GB (Q2_K) to 4.3 GB (Q8_0).

frankenmerger gemma 4b instruct v0.2 is a 4.05B-parameter Gemma model in GGUF format, quantized by RichardErkhov. Its trained context length is 8K tokens. The repository has 22 quant files, from 1.7 GB (Q2_K) to 4.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.7 GB 2.5 GB
Fits Get file →
IQ3_XS1.9 GB 2.6 GB
Fits Get file →
Q3_K_S2.0 GB 2.7 GB
Fits Get file →
IQ3_S2.0 GB 2.7 GB
Fits Get file →
IQ3_M2.0 GB 2.8 GB
Fits Get file →
Q3_K2.1 GB 2.9 GB
Fits Get file →
Q3_K_M2.1 GB 2.9 GB
Fits Get file →
Q3_K_L2.3 GB 3.0 GB
Fits Get file →
IQ4_XS2.3 GB 3.1 GB
Fits Get file →
Q4_02.4 GB 3.2 GB
Fits Get file →
Q4_K_S2.4 GB 3.2 GB
Fits Get file →
IQ4_NL2.4 GB 3.2 GB
Fits Get file →
Q4_K2.6 GB 3.3 GB
Fits Get file →
Q4_K_M2.6 GB 3.3 GB
Fits Get file →
Q4_12.6 GB 3.4 GB
Fits Get file →
Q5_02.9 GB 3.6 GB
Fits Get file →
Q5_K_S2.9 GB 3.6 GB
Fits Get file →
Q5_K2.9 GB 3.7 GB
Fits Get file →
Q5_K_M2.9 GB 3.7 GB
Fits Get file →
Q5_13.1 GB 3.8 GB
Fits Get file →
Q6_K3.3 GB 4.1 GB
Fits Get file →
Q8_04.3 GB 5.1 GB
Fits Get file →

What GPU do you need for frankenmerger gemma 4b instruct v0.2?

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: the best quant that fits is Q5_1 (3.1 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.1 GB in use).

Which frankenmerger gemma 4b instruct v0.2 quant should you choose?

Q4_K_M is the usual starting point for frankenmerger gemma 4b instruct v0.2: it balances file size and quality well. Here it is a 2.6 GB file.

The Q8_0 file is 4.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 1.7 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
Parameters4.05B
Layers32
Trained context8,192 tokens
KV cache (fp16)32 KB per token

Source

Quantized byRichardErkhov
FamilyGemma
Licenseapache-2.0
Downloads (HF)126
Last updated2024-10-04

Frequently asked questions about frankenmerger gemma 4b instruct v0.2

How much VRAM does frankenmerger gemma 4b instruct v0.2 need?

About 3.3 GB at Q4_K_M with an 8K context window. That is the 2.6 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 frankenmerger gemma 4b instruct v0.2 on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of frankenmerger gemma 4b instruct v0.2 GGUF?

It depends on the quant: Q2_K is 1.7 GB, IQ3_XS is 1.9 GB, Q3_K_S is 2.0 GB, IQ3_S is 2.0 GB, IQ3_M is 2.0 GB, Q3_K is 2.1 GB and 16 more.

What context length does frankenmerger gemma 4b instruct v0.2 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.3 GB at 8K.

Where can I download frankenmerger gemma 4b instruct v0.2 GGUF?

The files are on Hugging Face in the RichardErkhov/frankenmerger_-_gemma-4b-instruct-v0.2-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does frankenmerger gemma 4b instruct v0.2 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Gemma models

All Gemma →

Other small models

All small models →