Carnice V3 27b Pollard needs about 18.4 GB of memory at IQ4_XS (a 15.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 12.1 GB (IQ3_S) to 22.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Carnice V3 27b Pollard is a 27.3B-parameter Carnice model in GGUF format, quantized by PollardWeights. Its trained context length is 256K tokens. The repository has 3 quant files, from 12.1 GB (IQ3_S) to 22.4 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 12.1 GB | 14.8 GB | Too big | Get file → | |
| IQ4_XS | 15.7 GB | 18.4 GB | Too big | Get file → | |
| Q6_K | 22.4 GB | 25.1 GB | Too big | Get file → |
What GPU do you need for Carnice V3 27b Pollard?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ3_S (12.1 GB file, about 14.8 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_XS (15.7 GB file, about 18.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.4 GB file, about 25.1 GB in use).
Which Carnice V3 27b Pollard quant should you choose?
IQ4_XS (15.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ3_S at 12.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Carnice V3 27b Pollard
How much VRAM does Carnice V3 27b Pollard need?
About 18.4 GB at IQ4_XS with an 8K context window. That is the 15.7 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 Carnice V3 27b Pollard on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Carnice V3 27b Pollard GGUF?
It depends on the quant: IQ3_S is 12.1 GB, IQ4_XS is 15.7 GB, Q6_K is 22.4 GB.
What context length does Carnice V3 27b Pollard support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Carnice V3 27b Pollard GGUF?
The files are on Hugging Face in the PollardWeights/Carnice-V3-27b-Pollard repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Carnice V3 27b Pollard 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.