Phonellm Alpha 1 needs about 32.0 GB of memory at Q4_K_M (a 24.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 19.8 GB (Q3_K_M) to 63.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.
Phonellm Alpha 1 is a 31.6B-parameter Phonellm model in GGUF format, quantized by EryriLabs. Its trained context length is 1024K tokens. The repository has 4 quant files, from 19.8 GB (Q3_K_M) to 63.2 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 19.8 GB | 27.3 GB | Too big | Get file → | |
| Q4_K_M | 24.5 GB | 32.0 GB | Too big | Get file → | |
| Q8_0 | 33.6 GB | 41.1 GB | Too big | Get file → | |
| F16 | 63.2 GB | 70.7 GB | Too big | Get file → |
What GPU do you need for Phonellm Alpha 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: 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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q4_K_M (24.5 GB file, about 32.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (33.6 GB file, about 41.1 GB in use).
Which Phonellm Alpha 1 quant should you choose?
Q4_K_M is the usual starting point for Phonellm Alpha 1: it balances file size and quality well. Here it is a 24.5 GB file.
The Q8_0 file is 33.6 GB, about 1.4 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 Q3_K_M at 19.8 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 Phonellm Alpha 1
How much VRAM does Phonellm Alpha 1 need?
About 32.0 GB at Q4_K_M with an 8K context window. That is the 24.5 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 Phonellm Alpha 1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 27.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Phonellm Alpha 1 GGUF?
It depends on the quant: Q3_K_M is 19.8 GB, Q4_K_M is 24.5 GB, Q8_0 is 33.6 GB, F16 is 63.2 GB.
What context length does Phonellm Alpha 1 support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.0 GB at 8K and 27.9 GB at 32K.
Where can I download Phonellm Alpha 1 GGUF?
The files are on Hugging Face in the EryriLabs/phonellm-alpha-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 Phonellm Alpha 1 use?
Hugging Face lists the license as bsd-2-clause. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.