TE

TEA ASR 1.1

TeaGGUF by mradermacherUpdated 2026-10-26
Download on Hugging Face
Parameters1.72B
Context64K
Layers28
Architectureqwen3vl
Smallest quant0.8 GB
Quick answer

TEA ASR 1.1 needs about 2.5 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 11 quants, from 0.8 GB (Q2_K) to 1.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

TEA-ASR 1.1 – Taiwan Mandarin speech recognition in GGUF

TEA-ASR 1.1 is a 1.72B parameter model built on Qwen3VL. It delivers Traditional Chinese transcription with Taiwan vocabulary and robust Mandarin–English code‑switching. The model is available as a single GGUF checkpoint with multiple quantizations.

Good at

  • Taiwan Mandarin transcription
  • Code‑switching between Mandarin and English
  • Traditional Chinese output

Limits

  • No vision support
  • Requires at least 2.2 GB VRAM for Q2_K at 8k context
  • License is MIT

Best for

  • Transcribing Taiwanese podcasts
  • Localizing Mandarin audio content
  • Developing Taiwanese voice assistants

Who it’s for. Developers and researchers needing accurate Taiwan Mandarin speech recognition. The model is easy to integrate as a drop‑in replacement for Qwen3-ASR.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.8 GB 2.2 GB
Fits Get file →
Q3_K_S0.9 GB 2.3 GB
Fits Get file →
Q3_K_M0.9 GB 2.4 GB
Fits Get file →
Q3_K_L1.0 GB 2.4 GB
Fits Get file →
IQ4_XS1.0 GB 2.5 GB
Fits Get file →
Q4_K_S1.1 GB 2.5 GB
Fits Get file →
Q4_K_M1.1 GB 2.5 GB
Fits Get file →
Q5_K_S1.2 GB 2.7 GB
Fits Get file →
Q5_K_M1.3 GB 2.7 GB
Fits Get file →
Q6_K1.4 GB 2.9 GB
Fits Get file →
Q8_01.8 GB 3.3 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (1.11 GB file, 2.5 GB memory) is suitable. If memory is tighter, Q3_K_M (0.94 GB file, 2.4 GB memory) works. For maximum quality within 12 GB VRAM, Q8_0 (1.83 GB file, 3.3 GB memory) is recommended.

What GPU do you need for TEA ASR 1.1?

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 (1.8 GB file, about 3.3 GB in use).

Which TEA ASR 1.1 quant should you choose?

Q4_K_M is the usual starting point for TEA ASR 1.1: it balances file size and quality well. Here it is a 1.1 GB file.

The Q8_0 file is 1.8 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 0.8 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

Architectureqwen3vl
Parameters1.72B
Layers28
Trained context65,536 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymradermacher
FamilyTea
Licensemit
Downloads (HF)698
Last updated2026-10-26

Frequently asked questions about TEA ASR 1.1

How much VRAM does TEA ASR 1.1 need?

About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.1 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 TEA ASR 1.1 on an 8 GB GPU?

Yes, with Q8_0: the 1.8 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TEA ASR 1.1 GGUF?

It depends on the quant: Q2_K is 0.8 GB, Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, IQ4_XS is 1.0 GB, Q4_K_S is 1.1 GB and 5 more.

What context length does TEA ASR 1.1 support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download TEA ASR 1.1 GGUF?

The files are on Hugging Face in the mradermacher/TEA-ASR-1.1-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 TEA ASR 1.1 use?

Hugging Face lists the license as mit. 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 TEA-ASR 1.1 on 8 GB VRAM?

Yes, the Q4_K_M quant uses 2.5 GB memory at 8k context, fitting within 8 GB VRAM.

Does TEA-ASR 1.1 support vision tasks?

No, the model only supports speech recognition; no vision capabilities are included.

Other GGUFs of TEA-ASR-1.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Tea models

All Tea →

Other tiny models

All tiny models →