QW

Canary-Qwen 2.5B

QwenGGUF by handy-computerUpdated 2026-10-16
Download on Hugging Face
Parameters2.53B
Context—
Layers—
Architecturecanary_qwen
Smallest quant1.7 GB
Quick answer

Canary-Qwen 2.5B needs about 2.4 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 6 quants, from 1.7 GB (Q4_K_M) to 5.1 GB (F16).

Canary-Qwen 2.5B – English speech‑to‑text and LLM post‑processing

Canary‑Qwen‑2.5B is an English speech‑to‑text model with 2.5 billion parameters. It can transcribe 16 kHz mono WAV files and, in LLM mode, process the transcript for summarisation or question answering. The model is released under CC‑BY‑4.0.

Good at

  • Accurate English ASR
  • Post‑processing transcripts with LLM
  • Supports punctuation and capitalization

Limits

  • No vision or non‑English speech support
  • Requires 8 k context for full inference
  • License requires attribution

Best for

  • Transcribing podcasts
  • Generating meeting summaries
  • Answering questions about audio content

Who it’s for. Developers building offline English speech‑to‑text pipelines or applications that need transcript analysis. The model is suitable for commercial use under CC‑BY‑4.0.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.7 GB 2.4 GB
Fits Get file →
Q5_K_M2.0 GB 2.7 GB
Fits Get file →
Q6_K2.2 GB 3.0 GB
Fits Get file →
Q8_02.8 GB 3.6 GB
Fits Get file →
BF165.1 GB 6.2 GB
Fits Get file →
F165.1 GB 6.2 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.74 GB, ~2.4 GB RAM). For 12 GB VRAM, Q5_K_M (1.98 GB, ~2.7 GB RAM). For 16 GB VRAM, Q6_K (2.21 GB, ~3 GB RAM).

What GPU do you need for Canary-Qwen 2.5B?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (2.8 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.8 GB file, about 3.6 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.1 GB file, about 6.2 GB in use).

Which Canary-Qwen 2.5B quant should you choose?

Q4_K_M is the usual starting point for Canary-Qwen 2.5B: 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturecanary_qwen
Parameters2.53B

Source

Quantized byhandy-computer
FamilyQwen
Licensecc-by-4.0
Downloads (HF)28,842
Last updated2026-10-16

Frequently asked questions about Canary-Qwen 2.5B

How much VRAM does Canary-Qwen 2.5B need?

About 2.4 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 Canary-Qwen 2.5B on an 8 GB GPU?

Yes, with F16: the 5.1 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Canary-Qwen 2.5B GGUF?

It depends on the quant: Q4_K_M is 1.7 GB, Q5_K_M is 2.0 GB, Q6_K is 2.2 GB, Q8_0 is 2.8 GB, BF16 is 5.1 GB, F16 is 5.1 GB.

Where can I download Canary-Qwen 2.5B GGUF?

The files are on Hugging Face in the handy-computer/canary-qwen-2.5b-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 Canary-Qwen 2.5B use?

Hugging Face lists the license as cc-by-4.0. 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 Canary‑Qwen 2.5B on 8 GB VRAM?

Yes, the Q4_K_M quantised model is 1.74 GB and requires about 2.4 GB of RAM at 8 k context.

Does the model support languages other than English?

No, the model is trained and validated only for English speech.

Is the model free to use in commercial products?

Yes, it is released under the CC‑BY‑4.0 license, which allows commercial use with attribution.

Other GGUFs of canary-qwen-2.5b

Similar models

Browse all →

More from handy-computer

All by handy-computer →

More Qwen models

All Qwen →

Other tiny models

All tiny models →