FA

FairMind Minerva 3B Instruct v1.0

FairmindGGUF by RichardErkhovUpdated 2024-08-20
Download on Hugging Face
Parameters2.89B
Context16K
Layers32
Architecturellama
Smallest quant1.1 GB
Quick answer

FairMind Minerva 3B Instruct v1.0 needs about 2.9 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 1.1 GB (Q2_K) to 3.1 GB (Q8_0).

FairMind Minerva 3B Instruct v1.0 is a 2.89B-parameter Fairmind model in GGUF format, quantized by RichardErkhov. Its trained context length is 16K tokens. The repository has 22 quant files, from 1.1 GB (Q2_K) to 3.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.1 GB 2.3 GB
Fits Get file →
IQ3_XS1.2 GB 2.4 GB
Fits Get file →
Q3_K_S1.3 GB 2.4 GB
Fits Get file →
IQ3_S1.3 GB 2.5 GB
Fits Get file →
IQ3_M1.3 GB 2.5 GB
Fits Get file →
Q3_K1.4 GB 2.6 GB
Fits Get file →
Q3_K_M1.4 GB 2.6 GB
Fits Get file →
Q3_K_L1.5 GB 2.7 GB
Fits Get file →
IQ4_XS1.6 GB 2.8 GB
Fits Get file →
Q4_01.7 GB 2.8 GB
Fits Get file →
Q4_K_S1.7 GB 2.8 GB
Fits Get file →
IQ4_NL1.7 GB 2.8 GB
Fits Get file →
Q4_K1.8 GB 2.9 GB
Fits Get file →
Q4_K_M1.8 GB 2.9 GB
Fits Get file →
Q4_11.8 GB 3.0 GB
Fits Get file →
Q5_02.0 GB 3.2 GB
Fits Get file →
Q5_K_S2.0 GB 3.2 GB
Fits Get file →
Q5_K2.1 GB 3.2 GB
Fits Get file →
Q5_K_M2.1 GB 3.2 GB
Fits Get file →
Q5_12.2 GB 3.3 GB
Fits Get file →
Q6_K2.4 GB 3.5 GB
Fits Get file →
Q8_03.1 GB 4.2 GB
Fits Get file →

What GPU do you need for FairMind Minerva 3B Instruct v1.0?

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 Q6_K (2.4 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.1 GB file, about 4.2 GB in use).

Which FairMind Minerva 3B Instruct v1.0 quant should you choose?

Q4_K_M is the usual starting point for FairMind Minerva 3B Instruct v1.0: it balances file size and quality well. Here it is a 1.8 GB file.

The Q8_0 file is 3.1 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 1.1 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
Parameters2.89B
Layers32
Trained context16,384 tokens
KV cache (fp16)80 KB per token

Source

Quantized byRichardErkhov
FamilyFairmind
Downloads (HF)413
Last updated2024-08-20

Frequently asked questions about FairMind Minerva 3B Instruct v1.0

How much VRAM does FairMind Minerva 3B Instruct v1.0 need?

About 2.9 GB at Q4_K_M with an 8K context window. That is the 1.8 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 FairMind Minerva 3B Instruct v1.0 on an 8 GB GPU?

Yes, with Q8_0: the 3.1 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of FairMind Minerva 3B Instruct v1.0 GGUF?

It depends on the quant: Q2_K is 1.1 GB, IQ3_XS is 1.2 GB, Q3_K_S is 1.3 GB, IQ3_S is 1.3 GB, IQ3_M is 1.3 GB, Q3_K is 1.4 GB and 16 more.

What context length does FairMind Minerva 3B Instruct v1.0 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.7 GB at 8K and 1.3 GB at 16K.

Where can I download FairMind Minerva 3B Instruct v1.0 GGUF?

The files are on Hugging Face in the RichardErkhov/FairMind_-_Minerva-3B-Instruct-v1.0-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 FairMind Minerva 3B Instruct v1.0 use?

Hugging Face lists the license as cc-by-nc-sa-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

Other tiny models

All tiny models →