DA

Darkknight535 Moonlight L3 15B v2 64k

DarkknightGGUF by RichardErkhovUpdated 2024-10-31
Download on Hugging Face
Parameters15B
Context64K
Layers64
Architecturellama
Smallest quant3.0 GB
Quick answer

Darkknight535 Moonlight L3 15B v2 64k needs about 11.8 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 19 quants, from 3.0 GB (IQ4_XS) to 16.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Darkknight535 Moonlight L3 15B v2 64k is a 15B-parameter Darkknight model in GGUF format, quantized by RichardErkhov. Its trained context length is 64K tokens. The repository has 19 quant files, from 3.0 GB (IQ4_XS) to 16.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS3.0 GB 5.7 GB
Fits Get file →
Q4_03.6 GB 6.2 GB
Fits Get file →
Q3_K_L5.5 GB 8.2 GB
Too big Get file →
Q2_K5.7 GB 8.4 GB
Too big Get file →
Q3_K_S6.7 GB 9.3 GB
Too big Get file →
Q3_K7.4 GB 10.0 GB
Too big Get file →
Q3_K_M7.4 GB 10.0 GB
Too big Get file →
Q4_K_S8.6 GB 11.3 GB
Too big Get file →
IQ4_NL8.7 GB 11.3 GB
Too big Get file →
Q4_K9.1 GB 11.8 GB
Too big Get file →
Q4_K_M9.1 GB 11.8 GB
Too big Get file →
Q4_19.5 GB 12.1 GB
Too big Get file →
Q5_010.4 GB 13.0 GB
Too big Get file →
Q5_K_S10.4 GB 13.0 GB
Too big Get file →
Q5_K10.7 GB 13.3 GB
Too big Get file →
Q5_K_M10.7 GB 13.3 GB
Too big Get file →
Q5_111.3 GB 14.0 GB
Too big Get file →
Q6_K12.3 GB 15.0 GB
Too big Get file →
Q8_016.0 GB 18.6 GB
Too big Get file →

What GPU do you need for Darkknight535 Moonlight L3 15B v2 64k?

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 IQ4_XS (3.0 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_0 (3.6 GB file, about 6.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K (9.1 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.3 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (16.0 GB file, about 18.6 GB in use).

Which Darkknight535 Moonlight L3 15B v2 64k quant should you choose?

Q4_K_M is the usual starting point for Darkknight535 Moonlight L3 15B v2 64k: it balances file size and quality well. Here it is a 9.1 GB file.

The Q8_0 file is 16.0 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 IQ4_XS at 3.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters15B
Layers64
Trained context65,536 tokens
KV cache (fp16)256 KB per token

Source

Quantized byRichardErkhov
Downloads (HF)66
Last updated2024-10-31

Frequently asked questions about Darkknight535 Moonlight L3 15B v2 64k

How much VRAM does Darkknight535 Moonlight L3 15B v2 64k need?

About 11.8 GB at Q4_K_M with an 8K context window. That is the 9.1 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 Darkknight535 Moonlight L3 15B v2 64k on an 8 GB GPU?

Yes, with Q4_0: the 3.6 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Darkknight535 Moonlight L3 15B v2 64k GGUF?

It depends on the quant: IQ4_XS is 3.0 GB, Q4_0 is 3.6 GB, Q3_K_L is 5.5 GB, Q2_K is 5.7 GB, Q3_K_S is 6.7 GB, Q3_K is 7.4 GB and 13 more.

What context length does Darkknight535 Moonlight L3 15B v2 64k support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Darkknight535 Moonlight L3 15B v2 64k GGUF?

The files are on Hugging Face in the RichardErkhov/Darkknight535_-_Moonlight-L3-15B-v2-64k-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Darkknight models

All Darkknight →

Other medium models

All medium models →