FI

Finch 14B Final2

FinchGGUF by mradermacherUpdated 2024-09-11
Download on Hugging Face
Parameters14.1B
Context1024K
Layers61
Architecturerwkv6
Smallest quant5.4 GB
Quick answer

Finch 14B Final2 needs about 10.1 GB of memory at Q4_K_M (a 8.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 5.4 GB (Q2_K) to 15.4 GB (Q8_0).

Finch 14B Final2 is a 14.1B-parameter Finch model in GGUF format, quantized by mradermacher. Its trained context length is 1024K tokens. The repository has 14 quant files, from 5.4 GB (Q2_K) to 15.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 6.5 GB
Fits Get file →
IQ3_M6.7 GB 8.1 GB
Too big Get file →
IQ3_S6.7 GB 8.1 GB
Too big Get file →
IQ3_XS6.7 GB 8.1 GB
Too big Get file →
Q3_K_L6.7 GB 8.1 GB
Too big Get file →
Q3_K_M6.7 GB 8.1 GB
Too big Get file →
Q3_K_S6.7 GB 8.1 GB
Too big Get file →
IQ4_XS8.1 GB 9.6 GB
Too big Get file →
Q4_K_M8.6 GB 10.1 GB
Too big Get file →
Q4_K_S8.6 GB 10.1 GB
Too big Get file →
Q5_K_M10.3 GB 12.0 GB
Too big Get file →
Q5_K_S10.3 GB 12.0 GB
Too big Get file →
Q6_K12.1 GB 14.0 GB
Too big Get file →
Q8_015.4 GB 17.8 GB
Too big Get file →

What GPU do you need for Finch 14B Final2?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q2_K (5.4 GB file, about 6.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (10.3 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 14.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.4 GB file, about 17.8 GB in use).

Which Finch 14B Final2 quant should you choose?

Q4_K_M is the usual starting point for Finch 14B Final2: it balances file size and quality well. Here it is a 8.6 GB file.

The Q8_0 file is 15.4 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 5.4 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

Architecturerwkv6
Parameters14.1B
Layers61
Trained context1,048,576 tokens

Source

Quantized bymradermacher
FamilyFinch
Downloads (HF)105
Last updated2024-09-11

Frequently asked questions about Finch 14B Final2

How much VRAM does Finch 14B Final2 need?

About 10.1 GB at Q4_K_M with an 8K context window. That is the 8.6 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 Finch 14B Final2 on an 8 GB GPU?

Yes, with Q2_K: the 5.4 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Finch 14B Final2 GGUF?

It depends on the quant: Q2_K is 5.4 GB, IQ3_M is 6.7 GB, IQ3_S is 6.7 GB, IQ3_XS is 6.7 GB, Q3_K_L is 6.7 GB, Q3_K_M is 6.7 GB and 8 more.

What context length does Finch 14B Final2 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download Finch 14B Final2 GGUF?

The files are on Hugging Face in the mradermacher/Finch-14B-Final2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Finch-14B-Final2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Finch models

All Finch →

Other medium models

All medium models →