BitCPM CANN 3B unquantized needs about 1.7 GB of memory at TQ1_0 (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.9 GB (TQ1_0) to 1.1 GB (TQ2_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.
BitCPM CANN 3B unquantized is a 3.61B-parameter Bitcpm model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 2 quant files, from 0.9 GB (TQ1_0) to 1.1 GB (TQ2_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 0.9 GB | 1.7 GB | Fits | Get file → | |
| TQ2_0 | 1.1 GB | 1.9 GB | Fits | Get file → |
What GPU do you need for BitCPM CANN 3B unquantized?
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 TQ2_0 (1.1 GB file, about 1.9 GB in use).
Which BitCPM CANN 3B unquantized quant should you choose?
TQ1_0 (0.9 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about BitCPM CANN 3B unquantized
How much VRAM does BitCPM CANN 3B unquantized need?
About 1.7 GB at TQ1_0 with an 8K context window. That is the 0.9 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 BitCPM CANN 3B unquantized on an 8 GB GPU?
Yes, with TQ2_0: the 1.1 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of BitCPM CANN 3B unquantized GGUF?
It depends on the quant: TQ1_0 is 0.9 GB, TQ2_0 is 1.1 GB.
What context length does BitCPM CANN 3B unquantized support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.
Where can I download BitCPM CANN 3B unquantized GGUF?
The files are on Hugging Face in the mradermacher/BitCPM-CANN-3B-unquantized-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 BitCPM CANN 3B unquantized 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.