LU

luaqi sn29 v36

LuaqiGGUF by RichardErkhovUpdated 2024-10-05
Download on Hugging Face
Parameters5.63B
Context128K
Layers48
Architecturephi3
Smallest quant2.1 GB
Quick answer

luaqi sn29 v36 needs about 8.9 GB of memory at Q4_K_M (a 3.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 22 quants, from 2.1 GB (Q2_K) to 6.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 19.3 GB.

luaqi sn29 v36 is a 5.63B-parameter Luaqi model in GGUF format, quantized by RichardErkhov. Its trained context length is 128K tokens. The repository has 22 quant files, from 2.1 GB (Q2_K) to 6.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.1 GB 7.4 GB
Tight Get file →
IQ3_XS2.4 GB 7.7 GB
Tight Get file →
IQ3_S2.5 GB 7.8 GB
Tight Get file →
Q3_K_S2.5 GB 7.8 GB
Tight Get file →
IQ3_M2.7 GB 8.1 GB
Too big Get file →
Q3_K2.9 GB 8.2 GB
Too big Get file →
Q3_K_M2.9 GB 8.2 GB
Too big Get file →
IQ4_XS3.0 GB 8.4 GB
Too big Get file →
Q3_K_L3.1 GB 8.4 GB
Too big Get file →
Q4_03.2 GB 8.5 GB
Too big Get file →
IQ4_NL3.2 GB 8.5 GB
Too big Get file →
Q4_K_S3.2 GB 8.5 GB
Too big Get file →
Q4_K3.5 GB 8.9 GB
Too big Get file →
Q4_K_M3.5 GB 8.9 GB
Too big Get file →
Q4_13.5 GB 8.9 GB
Too big Get file →
Q5_03.9 GB 9.2 GB
Too big Get file →
Q5_K_S3.9 GB 9.2 GB
Too big Get file →
Q5_K4.1 GB 9.5 GB
Too big Get file →
Q5_K_M4.1 GB 9.5 GB
Too big Get file →
Q5_14.2 GB 9.6 GB
Too big Get file →
Q6_K4.6 GB 10.0 GB
Too big Get file →
Q8_06.0 GB 11.3 GB
Too big Get file →

What GPU do you need for luaqi sn29 v36?

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: the best quant that fits is IQ3_S (2.5 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (6.0 GB file, about 11.3 GB in use).

Which luaqi sn29 v36 quant should you choose?

Q4_K_M is the usual starting point for luaqi sn29 v36: it balances file size and quality well. Here it is a 3.5 GB file.

The Q8_0 file is 6.0 GB, about 1.7 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 2.1 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

Architecturephi3
Parameters5.63B
Layers48
Trained context131,072 tokens
KV cache (fp16)576 KB per token

Source

Quantized byRichardErkhov
FamilyLuaqi
Downloads (HF)5
Last updated2024-10-05

Frequently asked questions about luaqi sn29 v36

How much VRAM does luaqi sn29 v36 need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 3.5 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 luaqi sn29 v36 on an 8 GB GPU?

Yes, with IQ3_S: the 2.5 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 luaqi sn29 v36 GGUF?

It depends on the quant: Q2_K is 2.1 GB, IQ3_XS is 2.4 GB, IQ3_S is 2.5 GB, Q3_K_S is 2.5 GB, IQ3_M is 2.7 GB, Q3_K is 2.9 GB and 16 more.

What context length does luaqi sn29 v36 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.8 GB at 8K and 19.3 GB at 32K.

Where can I download luaqi sn29 v36 GGUF?

The files are on Hugging Face in the RichardErkhov/luaqi_-_sn29_v36-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 Luaqi models

All Luaqi →

Other small models

All small models →