QW

Vikhr-Qwen-2.5-1.5B-Instruct

QwenGGUF by VikhrmodelsUpdated 2024-11-26
Download on Hugging Face
Parameters1.54B
Context32K
Layers28
Architectureqwen2
Smallest quant0.4 GB
Quick answer

Vikhr-Qwen-2.5-1.5B-Instruct needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 30 quants, from 0.4 GB (IQ1_S) to 1.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

Qwen-2.5 1.5B instruct model for Russian and English

Vikhr-Qwen-2.5-1.5B-Instruct is a 1.54B parameter model based on Qwen-2.5. It was fine‑tuned on the GrandMaster-PRO-MAX dataset and supports 32,768 token context. The model is released under the Apache‑2.0 license.

Good at

  • Instruction following
  • Bilingual RU/EN text generation
  • Fast inference on modest GPUs

Limits

  • No vision support
  • Requires 8,192‑token context for best performance
  • License is Apache‑2.0

Best for

  • Chatbots needing Russian support
  • Text summarisation in RU/EN
  • Developer prototyping

Who it’s for. The model is suitable for developers and researchers who need a small, efficient instruction‑tuned model for Russian and English. It can be integrated into applications that require quick, accurate text responses.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.4 GB 1.2 GB
Fits Get file →
IQ1_M0.5 GB 1.2 GB
Fits Get file →
IQ2_XXS0.5 GB 1.2 GB
Fits Get file →
IQ2_XS0.6 GB 1.3 GB
Fits Get file →
IQ2_S0.6 GB 1.3 GB
Fits Get file →
IQ2_M0.6 GB 1.3 GB
Fits Get file →
Q2_K_S0.6 GB 1.4 GB
Fits Get file →
IQ3_XXS0.7 GB 1.4 GB
Fits Get file →
Q2_K0.7 GB 1.4 GB
Fits Get file →
IQ3_XS0.7 GB 1.5 GB
Fits Get file →
Q3_K_S0.8 GB 1.5 GB
Fits Get file →
IQ3_S0.8 GB 1.5 GB
Fits Get file →
IQ3_M0.8 GB 1.5 GB
Fits Get file →
Q3_K0.8 GB 1.6 GB
Fits Get file →
Q3_K_M0.8 GB 1.6 GB
Fits Get file →
Q3_K_L0.9 GB 1.6 GB
Fits Get file →
IQ4_XS0.9 GB 1.6 GB
Fits Get file →
Q4_00.9 GB 1.7 GB
Fits Get file →
IQ4_NL0.9 GB 1.7 GB
Fits Get file →
Q4_K_S0.9 GB 1.7 GB
Fits Get file →
Q4_K1.0 GB 1.7 GB
Fits Get file →
Q4_K_M1.0 GB 1.7 GB
Fits Get file →
Q4_11.0 GB 1.8 GB
Fits Get file →
Q5_01.1 GB 1.8 GB
Fits Get file →
Q5_K_S1.1 GB 1.8 GB
Fits Get file →
Q5_K1.1 GB 1.9 GB
Fits Get file →
Q5_K_M1.1 GB 1.9 GB
Fits Get file →
Q5_11.2 GB 1.9 GB
Fits Get file →
Q6_K1.3 GB 2.0 GB
Fits Get file →
Q8_01.6 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 (0.93 GB) or Q4_K (0.99 GB). For 4 GB VRAM, choose Q4_K_S (0.94 GB) or Q4_K_M (0.99 GB). For 2 GB VRAM, use Q4_K (0.99 GB) or Q4_K_M (0.99 GB).

What GPU do you need for Vikhr-Qwen-2.5-1.5B-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 Q8_0 (1.6 GB file, about 2.4 GB in use).

Which Vikhr-Qwen-2.5-1.5B-Instruct quant should you choose?

Q4_K_M is the usual starting point for Vikhr-Qwen-2.5-1.5B-Instruct: it balances file size and quality well. Here it is a 1.0 GB file.

The Q8_0 file is 1.6 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 0.4 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

Architectureqwen2
Parameters1.54B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized byVikhrmodels
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,571
Last updated2024-11-26

Frequently asked questions about Vikhr-Qwen-2.5-1.5B-Instruct

How much VRAM does Vikhr-Qwen-2.5-1.5B-Instruct need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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-Qwen-2.5-1.5B-Instruct on an 8 GB GPU?

Yes, with Q8_0: the 1.6 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Vikhr-Qwen-2.5-1.5B-Instruct GGUF?

It depends on the quant: IQ1_S is 0.4 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.5 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.6 GB, IQ2_M is 0.6 GB and 24 more.

What context length does Vikhr-Qwen-2.5-1.5B-Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download Vikhr-Qwen-2.5-1.5B-Instruct GGUF?

The files are on Hugging Face in the Vikhrmodels/Vikhr-Qwen-2.5-1.5B-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-Qwen-2.5-1.5B-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 this model on 8 GB VRAM?

Yes, the Q4_0 and Q4_K variants are under 1 GB and will run on 8 GB VRAM.

Does the model support vision tasks?

No, the model is text‑only and does not support vision.

What context length does it support?

The model was trained with 32,768 token context and performs best with that length.

Other GGUFs of Vikhr-Qwen-2.5-1.5B-Instruct

Similar models

Browse all →

More from Vikhrmodels

All by Vikhrmodels →

More Qwen models

All Qwen →

Other tiny models

All tiny models →