GE

EZO-Humanities-9B-gemma-2-it

GemmaGGUF by mmngaUpdated 2024-07-15
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant2.4 GB
Quick answer

EZO-Humanities-9B-gemma-2-it needs about 9.1 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.4 GB (IQ1_S) to 9.8 GB (Q8_0).

EZO-Humanities-9B gemma2 model in GGUF format

EZO-Humanities-9B gemma2 is a 9.24B parameter model trained on 8192 token context. It is available in multiple GGUF quantizations from IQ1_S to Q8_0. The model supports English and Japanese.

Good at

  • Japanese language tasks
  • English language tasks
  • Long context reasoning

Limits

  • No vision support
  • License: gemma
  • Requires 8k context for full performance

Best for

  • Chatbot development
  • Text generation in Japanese
  • Contextual analysis

Who it’s for. Developers building local LLM applications that need a large gemma2 model with Japanese support. The model is suitable for users who can run GGUF files on llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.4 GB 5.7 GB
Fits Get file →
IQ1_M2.5 GB 5.9 GB
Fits Get file →
IQ2_XXS2.8 GB 6.1 GB
Fits Get file →
IQ2_XS3.1 GB 6.4 GB
Fits Get file →
IQ2_S3.2 GB 6.5 GB
Fits Get file →
IQ2_M3.4 GB 6.8 GB
Fits Get file →
IQ3_XXS3.8 GB 7.1 GB
Fits Get file →
Q2_K3.8 GB 7.1 GB
Fits Get file →
IQ3_XS4.1 GB 7.5 GB
Tight Get file →
Q3_K_S4.3 GB 7.7 GB
Tight Get file →
IQ3_S4.3 GB 7.7 GB
Tight Get file →
IQ3_M4.5 GB 7.8 GB
Tight Get file →
Q3_K_M4.8 GB 8.1 GB
Too big Get file →
Q3_K_L5.1 GB 8.5 GB
Too big Get file →
IQ4_XS5.2 GB 8.5 GB
Too big Get file →
Q4_05.4 GB 8.8 GB
Too big Get file →
IQ4_NL5.4 GB 8.8 GB
Too big Get file →
Q4_K_S5.5 GB 8.8 GB
Too big Get file →
Q4_K_M5.8 GB 9.1 GB
Too big Get file →
Q5_06.5 GB 9.8 GB
Too big Get file →
Q5_K_S6.5 GB 9.8 GB
Too big Get file →
Q5_K_M6.6 GB 10.0 GB
Too big Get file →
Q6_K7.6 GB 10.9 GB
Too big Get file →
Q8_09.8 GB 13.1 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XS (3.07 GB) or IQ2_S (3.21 GB). For 12 GB VRAM, IQ4_K_M (5.76 GB) or Q5_K_M (6.65 GB) are suitable. Larger VRAM allows Q6_K (7.59 GB) or Q8_0 (9.83 GB).

What GPU do you need for EZO-Humanities-9B-gemma-2-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: the best quant that fits is IQ1_M (2.5 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_M (4.5 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.6 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 13.1 GB in use).

Which EZO-Humanities-9B-gemma-2-it quant should you choose?

Q4_K_M is the usual starting point for EZO-Humanities-9B-gemma-2-it: it balances file size and quality well. Here it is a 5.8 GB file.

The Q8_0 file is 9.8 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 IQ1_S at 2.4 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

Architecturegemma2
Parameters9.24B
Layers42
Trained context8,192 tokens
KV cache (fp16)336 KB per token

Source

Quantized bymmnga
FamilyGemma
Licensegemma
Downloads (HF)864
Last updated2024-07-15

Frequently asked questions about EZO-Humanities-9B-gemma-2-it

How much VRAM does EZO-Humanities-9B-gemma-2-it need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 5.8 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 EZO-Humanities-9B-gemma-2-it on an 8 GB GPU?

Yes, with IQ3_M: the 4.5 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of EZO-Humanities-9B-gemma-2-it GGUF?

It depends on the quant: IQ1_S is 2.4 GB, IQ1_M is 2.5 GB, IQ2_XXS is 2.8 GB, IQ2_XS is 3.1 GB, IQ2_S is 3.2 GB, IQ2_M is 3.4 GB and 18 more.

What context length does EZO-Humanities-9B-gemma-2-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 2.8 GB at 8K and 2.8 GB at 8K.

Where can I download EZO-Humanities-9B-gemma-2-it GGUF?

The files are on Hugging Face in the mmnga/HODACHI-EZO-Humanities-9B-gemma-2-it-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 EZO-Humanities-9B-gemma-2-it use?

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

Can I run this model on 8 GB VRAM?

Yes, use IQ2_XS or IQ2_S quantizations. They require about 6.4–6.5 GB memory at 8k context.

Does this model support vision?

No, the model has no vision capabilities.

What languages does it support?

English and Japanese.

Similar models

Browse all →

More from mmnga

All by mmnga →

More Gemma models

All Gemma →

Other small models

All small models →