MI

P3 mini v3

MiniGGUF by mradermacherUpdated 2024-08-23
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant1.4 GB
Quick answer

P3 mini v3 needs about 6.0 GB of memory at Q4_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 1.4 GB (Q2_K) to 7.6 GB (F16).

P3 mini v3 is a 3.82B-parameter Mini model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 15 quant files, from 1.4 GB (Q2_K) to 7.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.4 GB 3.6 GB
Fits Get file →
IQ3_XS1.6 GB 3.7 GB
Fits Get file →
IQ3_S1.7 GB 3.8 GB
Fits Get file →
Q3_K_S1.7 GB 3.8 GB
Fits Get file →
IQ3_M1.8 GB 3.9 GB
Fits Get file →
Q3_K_M1.9 GB 4.0 GB
Fits Get file →
Q3_K_L2.0 GB 4.2 GB
Fits Get file →
IQ4_XS2.1 GB 4.2 GB
Fits Get file →
Q4_K_S2.2 GB 4.3 GB
Fits Get file →
Q4_K_M2.3 GB 4.4 GB
Fits Get file →
Q5_K_S2.6 GB 4.8 GB
Fits Get file →
Q5_K_M2.7 GB 4.8 GB
Fits Get file →
Q6_K3.1 GB 5.2 GB
Fits Get file →
Q8_04.1 GB 6.2 GB
Fits Get file →
F167.6 GB 9.8 GB
Too big Get file →

What GPU do you need for P3 mini v3?

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: the best quant that fits is Q4_K_M (2.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (7.6 GB file, about 11.4 GB in use).

Which P3 mini v3 quant should you choose?

Q4_K_M is the usual starting point for P3 mini v3: it balances file size and quality well. Here it is a 2.3 GB file.

The Q8_0 file is 4.1 GB, about 1.8 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 Q2_K at 1.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymradermacher
FamilyMini
Licenseapache-2.0
Downloads (HF)335
Last updated2024-08-23

Frequently asked questions about P3 mini v3

How much VRAM does P3 mini v3 need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 2.3 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 P3 mini v3 on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of P3 mini v3 GGUF?

It depends on the quant: Q2_K is 1.4 GB, IQ3_XS is 1.6 GB, IQ3_S is 1.7 GB, Q3_K_S is 1.7 GB, IQ3_M is 1.8 GB, Q3_K_M is 1.9 GB and 9 more.

What context length does P3 mini v3 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download P3 mini v3 GGUF?

The files are on Hugging Face in the mradermacher/P3-mini-v3-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 P3 mini v3 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.

Other GGUFs of P3-mini-v3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mini models

All Mini →

Other small models

All small models →