Cohere Transcribe 03-2026 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 1.3 GB (Q4_K) to 4.1 GB.
Cohere Transcribe 03-2026 – 2.07B‑parameter open‑source ASR model
Cohere Transcribe 03-2026 is a 2.07‑billion‑parameter ASR model converted to GGUF. It supports 14 listed languages and can run on CPU via CrispASR. The model is licensed under Apache‑2.0.
Good at
- Accurate transcription with low WER
- CPU‑friendly inference
- Supports 14 common languages
Limits
- No vision support
- Requires 8‑k context for memory estimates
- No explicit language detection runtime signal
Best for
- Transcribing short audio clips
- Integrating into CPU‑only pipelines
- Deploying in low‑resource environments
Who it’s for. Developers building speech‑to‑text services on commodity hardware. Researchers needing a lightweight, open‑source ASR model for experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 1.3 GB | 1.9 GB | Fits | Get file → | |
| Q5_0 | 1.7 GB | 2.4 GB | Fits | Get file → | |
| Q5_1 | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q6_K | 2.0 GB | 2.7 GB | Fits | Get file → | |
| Q8_0 | 2.4 GB | 3.2 GB | Fits | Get file → | |
| — | 4.1 GB | 5.1 GB | Fits | Get file → |
For 8‑GB VRAM, Q4_K (1.29 GB) or Q5_0 (1.74 GB) are suitable, using about 1.9–2.4 GB of RAM 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 uses 4.14 GB and 5.1 GB memory.
What GPU do you need for Cohere Transcribe 03-2026?
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 03-2026 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 1.3 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
Source
Frequently asked questions about Cohere Transcribe 03-2026
How much VRAM does Cohere Transcribe 03-2026 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 03-2026 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 03-2026 GGUF?
It depends on the quant: Q4_K is 1.3 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 03-2026 GGUF?
The files are on Hugging Face in the cstr/cohere-transcribe-03-2026-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 Cohere Transcribe 03-2026 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 Cohere Transcribe 03-2026 on 8 GB VRAM?
Yes, the Q4_K or Q5_0 quantized files fit within 8 GB VRAM and use about 1.9–2.4 GB of RAM at 8‑k context.
Does the model support languages beyond the 14 listed?
The tokenizer contains 183 ISO‑639‑1 tokens, but runtime language checks use the 14‑language whitelist. Unsupported languages will be processed but may not be flagged.
What license applies to the GGUF weights?
The GGUF weights are released under Apache‑2.0, inherited from the original Cohere model.