GE

Hebrew Gemma 11B Instruct

GemmaGGUF by mradermacherUpdated 2024-12-03
Download on Hugging Face
Parameters10.5B
Context8K
Layers35
Architecturegemma
Smallest quant2.6 GB
Quick answer

Hebrew Gemma 11B Instruct needs about 11.7 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 2.6 GB (IQ1_S) to 8.6 GB (Q6_K).

Hebrew Gemma 11B Instruct – a 10.5B parameter instruction‑tuned Gemma model

Hebrew Gemma 11B Instruct is a 10.5B parameter LLM fine‑tuned for instruction following. It supports Hebrew and English text and uses a 8192 token context window. The model is distributed in GGUF format with multiple quantization options.

Good at

  • Instruction following in Hebrew and English
  • Chat‑style interactions
  • Text generation with 8192 token context

Limits

  • No vision support
  • License is other, not open source
  • Requires 8k context for memory estimates

Best for

  • Developers building Hebrew chatbots
  • Researchers testing instruction fine‑tuning
  • Users needing a large Hebrew‑English LLM

Who it’s for. This model is intended for developers and researchers who need a large instruction‑tuned LLM that handles Hebrew and English. It is suitable for building chat applications or conducting research on multilingual instruction following.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.6 GB 7.8 GB
Tight Get file →
IQ1_M2.8 GB 8.0 GB
Tight Get file →
IQ2_XXS3.1 GB 8.3 GB
Too big Get file →
IQ2_XS3.4 GB 8.6 GB
Too big Get file →
IQ2_S3.5 GB 8.7 GB
Too big Get file →
IQ2_M3.8 GB 9.0 GB
Too big Get file →
Q2_K_S3.9 GB 9.1 GB
Too big Get file →
Q2_K4.2 GB 9.4 GB
Too big Get file →
IQ3_XXS4.2 GB 9.4 GB
Too big Get file →
IQ3_XS4.6 GB 9.8 GB
Too big Get file →
IQ3_S4.8 GB 10.0 GB
Too big Get file →
Q3_K_S4.8 GB 10.0 GB
Too big Get file →
IQ3_M5.0 GB 10.2 GB
Too big Get file →
Q3_K_M5.3 GB 10.5 GB
Too big Get file →
Q3_K_L5.7 GB 10.9 GB
Too big Get file →
IQ4_XS5.8 GB 11.0 GB
Too big Get file →
Q4_06.1 GB 11.3 GB
Too big Get file →
Q4_06.1 GB 11.3 GB
Too big Get file →
Q4_06.1 GB 11.3 GB
Too big Get file →
Q4_06.1 GB 11.3 GB
Too big Get file →
Q4_K_S6.1 GB 11.3 GB
Too big Get file →
Q4_K_M6.5 GB 11.7 GB
Too big Get file →
Q5_K_S7.3 GB 12.5 GB
Too big Get file →
Q5_K_M7.5 GB 12.7 GB
Too big Get file →
Q6_K8.6 GB 13.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.57 GB, estimated 7.8 GB memory). If 12 GB VRAM is available, IQ2_XS (3.38 GB, 8.6 GB memory) or Q3_K_M (5.31 GB, 10.5 GB memory) are suitable. For 16 GB VRAM, Q4_K_M (6.49 GB, 11.7 GB memory) or Q5_K_M (7.51 GB, 12.7 GB memory) can be used.

What GPU do you need for Hebrew Gemma 11B Instruct?

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 IQ1_M (2.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (6.5 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (8.6 GB file, about 13.8 GB in use).

Which Hebrew Gemma 11B Instruct quant should you choose?

Q4_K_M is the usual starting point for Hebrew Gemma 11B Instruct: it balances file size and quality well. Here it is a 6.5 GB file.

If memory is tight, the smallest file is IQ1_S at 2.6 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
Parameters10.5B
Layers35
Trained context8,192 tokens
KV cache (fp16)560 KB per token

Source

Quantized bymradermacher
FamilyGemma
Licenseother
Downloads (HF)650
Last updated2024-12-03

Frequently asked questions about Hebrew Gemma 11B Instruct

How much VRAM does Hebrew Gemma 11B Instruct need?

About 11.7 GB at Q4_K_M with an 8K context window. That is the 6.5 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 Hebrew Gemma 11B Instruct on an 8 GB GPU?

Yes, with IQ1_M: the 2.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hebrew Gemma 11B Instruct GGUF?

It depends on the quant: IQ1_S is 2.6 GB, IQ1_M is 2.8 GB, IQ2_XXS is 3.1 GB, IQ2_XS is 3.4 GB, IQ2_S is 3.5 GB, IQ2_M is 3.8 GB and 19 more.

What context length does Hebrew Gemma 11B Instruct support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 4.7 GB at 8K and 4.7 GB at 8K.

Where can I download Hebrew Gemma 11B Instruct GGUF?

The files are on Hugging Face in the mradermacher/Hebrew-Gemma-11B-Instruct-i1-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 Hebrew Gemma 11B Instruct use?

Hugging Face lists the license as other. 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 Hebrew Gemma 11B Instruct on 8 GB VRAM?

Yes, the IQ1_S quant requires about 7.8 GB memory at 8k context, which fits within 8 GB VRAM.

Does the model support vision tasks?

No, the model has no vision support.

What is the context length of the model?

The model is trained with a 8192 token context window.

Other GGUFs of Hebrew-Gemma-11B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other medium models

All medium models →