CO

cohere transcribe ja v0.1

CohereGGUF by TransWithAIUpdated 2026-05-16
Download on Hugging Face
Parameters2.07B
Context—
Layers—
Architecturecohere-transcribe
Smallest quant1.5 GB
Quick answer

cohere transcribe ja v0.1 needs about 2.6 GB of memory at Q5_1 (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 1.5 GB (Q4_K) to 4.1 GB.

Japanese ASR model fine‑tuned from Cohere Transcribe

cohere transcribe ja v0.1 is a 2.07 billion‑parameter Japanese speech‑to‑text model. It was trained on 2^17 steps with a batch size of 64 and averages 25.3 s audio samples. The model is available in multiple GGUF quantizations.

Good at

  • Japanese speech transcription
  • Anime domain content
  • Low‑latency inference

Limits

  • No vision support
  • License not explicitly declared
  • No HPO

Best for

  • Transcribing Japanese podcasts
  • Generating subtitles for anime
  • Voice‑to‑text in Japanese apps

Who it’s for. Developers needing a Japanese ASR model for production or research. The model is suitable for applications that require accurate transcription of spoken Japanese, especially in anime or general domains.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K1.5 GB 2.2 GB
Fits Get file →
Q5_01.7 GB 2.4 GB
Fits Get file →
Q5_11.9 GB 2.6 GB
Fits Get file →
Q6_K2.0 GB 2.7 GB
Fits Get file →
Q8_02.4 GB 3.2 GB
Fits Get file →
—4.1 GB 5.1 GB
Fits Get file →

For 8 GB VRAM, Q4_K (1.51 GB) or Q5_0 (1.74 GB) are suitable, estimating 2.2–2.4 GB memory at 8 k context. If more memory is available, Q6_K (1.98 GB) or Q8_0 (2.42 GB) provide higher precision. The unknown quant requires 4.14 GB and 5.1 GB memory, which is best for high‑end GPUs.

What GPU do you need for cohere transcribe ja v0.1?

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 (2.4 GB file, about 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (4.1 GB file, about 5.1 GB in use).

Which cohere transcribe ja v0.1 quant should you choose?

Q5_1 (1.9 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q4_K at 1.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturecohere-transcribe
Parameters2.07B

Source

Quantized byTransWithAI
FamilyCohere
Downloads (HF)1,468
Last updated2026-05-16

Frequently asked questions about cohere transcribe ja v0.1

How much VRAM does cohere transcribe ja v0.1 need?

About 2.6 GB at Q5_1 with an 8K context window. That is the 1.9 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 cohere transcribe ja v0.1 on an 8 GB GPU?

Yes, with the smaller files: the 4.1 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of cohere transcribe ja v0.1 GGUF?

It depends on the quant: Q4_K is 1.5 GB, Q5_0 is 1.7 GB, Q5_1 is 1.9 GB, Q6_K is 2.0 GB, Q8_0 is 2.4 GB, file is 4.1 GB.

Where can I download cohere transcribe ja v0.1 GGUF?

The files are on Hugging Face in the TransWithAI/cohere-transcribe-ja-v0.1-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 and Q5_0 quantizations fit within 8 GB VRAM, using approximately 2.2–2.4 GB memory at 8 k context.

Does this model support English?

No, the model is fine‑tuned for Japanese and does not support other languages.

What license applies to this model?

The base Cohere Transcribe model is Apache‑2.0; the fine‑tune repository does not declare an explicit license, so check the source model card before redistribution or commercial use.

Similar models

Browse all →

More from TransWithAI

All by TransWithAI →

More Cohere models

All Cohere →

Other tiny models

All tiny models →