GE

Vikhr-Gemma-2B-instruct

GemmaGGUF by RichardErkhovUpdated 2024-08-22
Download on Hugging Face
Parameters2.61B
Context8K
Layers26
Architecturegemma2
Smallest quant1.2 GB
Quick answer

Vikhr-Gemma-2B-instruct needs about 3.1 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 1.2 GB (Q2_K) to 2.8 GB (Q8_0).

Vikhr-Gemma-2B-instruct – a 2.61B parameter instruct model for Russian

Vikhr-Gemma-2B-instruct is a 2.61B parameter Gemma 2 model fine‑tuned on the GrandMaster‑PRO‑MAX Russian dataset. It supports instruction following and is available in multiple GGUF quantizations. The model is licensed under apache‑2.0.

Good at

  • Instruction following in Russian
  • Compact size for local deployment
  • Low‑latency inference with GGUF

Limits

  • No vision support
  • Maximum context length 8192 tokens
  • Requires at least 2.6 GB VRAM for Q2_K

Best for

  • Chatbots in Russian
  • Local language tutoring
  • Rapid prototyping of Russian NLP tools

Who it’s for. Developers building Russian‑language applications who need a small, instruction‑capable model. Researchers wanting a lightweight Gemma variant for experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.2 GB 2.6 GB
Fits Get file →
IQ3_XS1.3 GB 2.7 GB
Fits Get file →
IQ3_S1.4 GB 2.7 GB
Fits Get file →
Q3_K_S1.4 GB 2.7 GB
Fits Get file →
IQ3_M1.4 GB 2.8 GB
Fits Get file →
Q3_K1.5 GB 2.8 GB
Fits Get file →
Q3_K_M1.5 GB 2.8 GB
Fits Get file →
Q3_K_L1.6 GB 2.9 GB
Fits Get file →
IQ4_XS1.6 GB 2.9 GB
Fits Get file →
Q4_01.6 GB 3.0 GB
Fits Get file →
IQ4_NL1.6 GB 3.0 GB
Fits Get file →
Q4_K_S1.6 GB 3.0 GB
Fits Get file →
Q4_K1.7 GB 3.1 GB
Fits Get file →
Q4_K_M1.7 GB 3.1 GB
Fits Get file →
Q4_11.8 GB 3.1 GB
Fits Get file →
Q5_01.9 GB 3.3 GB
Fits Get file →
Q5_K_S1.9 GB 3.3 GB
Fits Get file →
Q5_K1.9 GB 3.3 GB
Fits Get file →
Q5_K_M1.9 GB 3.3 GB
Fits Get file →
Q5_12.0 GB 3.4 GB
Fits Get file →
Q6_K2.2 GB 3.5 GB
Fits Get file →
Q8_02.8 GB 4.2 GB
Fits Get file →

For 8 GB VRAM, use Q4_K or Q4_K_M (file size 1.71 GB, memory ~3.1 GB). If 4 GB VRAM is available, Q3_K or Q3_K_S (file size 1.36 GB, memory ~2.7 GB) is recommended. For the smallest memory footprint, Q2_K (file size 1.23 GB, memory ~2.6 GB) can be used on 4 GB VRAM with reduced precision.

What GPU do you need for Vikhr-Gemma-2B-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: the best quant that fits is Q6_K (2.2 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.8 GB file, about 4.2 GB in use).

Which Vikhr-Gemma-2B-instruct quant should you choose?

Q4_K_M is the usual starting point for Vikhr-Gemma-2B-instruct: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 2.8 GB, about 1.6 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 1.2 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
Parameters2.61B
Layers26
Trained context8,192 tokens
KV cache (fp16)104 KB per token

Source

Quantized byRichardErkhov
FamilyGemma
Licenseapache-2.0
Downloads (HF)1,193
Last updated2024-08-22

Frequently asked questions about Vikhr-Gemma-2B-instruct

How much VRAM does Vikhr-Gemma-2B-instruct need?

About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.7 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 Vikhr-Gemma-2B-instruct on an 8 GB GPU?

Yes, with Q8_0: the 2.8 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Vikhr-Gemma-2B-instruct GGUF?

It depends on the quant: Q2_K is 1.2 GB, IQ3_XS is 1.3 GB, IQ3_S is 1.4 GB, Q3_K_S is 1.4 GB, IQ3_M is 1.4 GB, Q3_K is 1.5 GB and 16 more.

What context length does Vikhr-Gemma-2B-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 0.9 GB at 8K and 0.9 GB at 8K.

Where can I download Vikhr-Gemma-2B-instruct GGUF?

The files are on Hugging Face in the RichardErkhov/Vikhrmodels_-_Vikhr-Gemma-2B-instruct-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 Vikhr-Gemma-2B-instruct 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.

Can I run Vikhr-Gemma-2B-instruct on 8 GB VRAM?

Yes, use Q4_K or Q4_K_M quantizations; they require about 3.1 GB VRAM at 8k context.

Does the model support English?

The model is specialized for Russian; English performance is not guaranteed.

Is the model free to use?

Yes, it is licensed under apache‑2.0, allowing free use and modification.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Gemma models

All Gemma →

Other tiny models

All tiny models →