QW

ruadapt_qwen2.5_7B_ext_u48_instruct

QwenGGUF by RefalMachineUpdated 2024-12-31
Download on Hugging Face
Parameters7.58B
Context32K
Layers28
Architectureqwen2
Smallest quant3.0 GB
Quick answer

ruadapt_qwen2.5_7B_ext_u48_instruct needs about 5.6 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 9 quants, from 3.0 GB (Q2_K) to 15.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Qwen2.5‑7B adapted for Russian instruction

ruadapt_qwen2.5_7B_ext_u48_instruct is a 7.58 billion‑parameter Qwen model fine‑tuned on Russian text. It uses an extended tiktoken cl100k tokenizer with 48 k tokens and supports tool usage. The model is available in multiple GGUF quantizations.

Good at

  • Russian instruction following
  • Tool invocation
  • Fast generation on 8 k context

Limits

  • No vision support
  • License not specified
  • Large context requires 32 768 tokens

Best for

  • Chatbots in Russian
  • Russian text generation
  • Tool‑enabled assistants

Who it’s for. Developers building Russian‑language LLM applications who need instruction following and tool use. The model is suitable for local deployment with GGUF support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.0 GB 4.0 GB
Fits Get file →
Q3_K_M3.8 GB 4.8 GB
Fits Get file →
Q4_04.4 GB 5.4 GB
Fits Get file →
Q4_K_M4.7 GB 5.6 GB
Fits Get file →
Q5_05.3 GB 6.3 GB
Fits Get file →
Q5_K_M5.4 GB 6.4 GB
Fits Get file →
Q6_K6.2 GB 7.2 GB
Fits Get file →
Q8_08.1 GB 9.0 GB
Too big Get file →
—15.2 GB 16.1 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (file size 4.66 GB, estimated 5.6 GB memory). For 16 GB VRAM use Q5_K_M (5.42 GB, 6.4 GB memory). Larger models require more VRAM.

What GPU do you need for ruadapt_qwen2.5_7B_ext_u48_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 Q2_K (3.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.7 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.2 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.0 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (15.2 GB file, about 16.1 GB in use).

Which ruadapt_qwen2.5_7B_ext_u48_instruct quant should you choose?

Q4_K_M is the usual starting point for ruadapt_qwen2.5_7B_ext_u48_instruct: it balances file size and quality well. Here it is a 4.7 GB file.

The Q8_0 file is 8.1 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 3.0 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
Parameters7.58B
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized byRefalMachine
FamilyQwen
Downloads (HF)398
Last updated2024-12-31

Frequently asked questions about ruadapt_qwen2.5_7B_ext_u48_instruct

How much VRAM does ruadapt_qwen2.5_7B_ext_u48_instruct need?

About 5.6 GB at Q4_K_M with an 8K context window. That is the 4.7 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 ruadapt_qwen2.5_7B_ext_u48_instruct on an 8 GB GPU?

Yes, with Q6_K: the 6.2 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ruadapt_qwen2.5_7B_ext_u48_instruct GGUF?

It depends on the quant: Q2_K is 3.0 GB, Q3_K_M is 3.8 GB, Q4_0 is 4.4 GB, Q4_K_M is 4.7 GB, Q5_0 is 5.3 GB, Q5_K_M is 5.4 GB and 3 more.

What context length does ruadapt_qwen2.5_7B_ext_u48_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 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download ruadapt_qwen2.5_7B_ext_u48_instruct GGUF?

The files are on Hugging Face in the RefalMachine/ruadapt_qwen2.5_7B_ext_u48_instruct_gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 5.6 GB of VRAM at 8 k context, which fits in 8 GB.

Does this model support vision?

No, the model has no vision capabilities.

What context length does it support?

It supports up to 32 768 tokens of context.

Similar models

Browse all →

More from RefalMachine

All by RefalMachine →

More Qwen models

All Qwen →

Other small models

All small models →