LM

LMCocktail 10.7B v1

LmcocktailGGUF by andrijdavidUpdated 2023-12-27
Download on Hugging Face
Parameters10.7B
Context4K
Layers48
Architecturellama
Smallest quant0.0 GB
Quick answer

LMCocktail 10.7B v1 needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 18 quants, from 0.0 GB (Q5_K_M) to 21.5 GB (F16).

LMCocktail 10.7B v1 is a 10.7B-parameter Lmcocktail model in GGUF format, quantized by andrijdavid. Its trained context length is 4K tokens. The repository has 18 quant files, from 1.7 GB (Q5_K_S) to 21.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M0.0 GB 1.3 GB
Fits Get file →
Q6_K0.0 GB 1.3 GB
Fits Get file →
Q8_00.0 GB 1.3 GB
Fits Get file →
Q5_K_S1.7 GB 3.0 GB
Fits Get file →
Q2_K4.5 GB 5.9 GB
Fits Get file →
Q3_K_S4.7 GB 6.0 GB
Fits Get file →
Q3_K5.2 GB 6.5 GB
Fits Get file →
Q3_K_M5.2 GB 6.5 GB
Fits Get file →
Q3_K_L5.7 GB 7.0 GB
Fits Get file →
Q4_06.1 GB 7.4 GB
Tight Get file →
Q4_K_S6.1 GB 7.4 GB
Tight Get file →
Q4_K6.5 GB 7.8 GB
Tight Get file →
Q4_K_M6.5 GB 7.8 GB
Tight Get file →
Q4_16.7 GB 8.0 GB
Too big Get file →
Q5_07.4 GB 8.7 GB
Too big Get file →
Q5_K7.6 GB 8.9 GB
Too big Get file →
Q5_18.1 GB 9.4 GB
Too big Get file →
F1621.5 GB 22.8 GB
Too big Get file →

What GPU do you need for LMCocktail 10.7B v1?

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 Q5_K_S (1.7 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_S (1.7 GB file, about 3.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_L (5.7 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_1 (8.1 GB file, about 10.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_1 (8.1 GB file, about 10.2 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (21.5 GB file, about 23.6 GB in use).

Which LMCocktail 10.7B v1 quant should you choose?

Q4_K_M is the usual starting point for LMCocktail 10.7B v1: it balances file size and quality well. Here it is a 6.5 GB file.

The Q8_0 file is 0.0 GB, about 0.0 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 Q5_K_M at 0.0 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.7B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized byandrijdavid
Licensellama2
Downloads (HF)200
Last updated2023-12-27

Frequently asked questions about LMCocktail 10.7B v1

How much VRAM does LMCocktail 10.7B v1 need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 LMCocktail 10.7B v1 on an 8 GB GPU?

Yes, with Q3_K_L: the 5.7 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 LMCocktail 10.7B v1 GGUF?

It depends on the quant: Q5_K_M is 0.0 GB, Q6_K is 0.0 GB, Q8_0 is 0.0 GB, Q5_K_S is 1.7 GB, Q2_K is 4.5 GB, Q3_K_S is 4.7 GB and 12 more.

What context length does LMCocktail 10.7B v1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download LMCocktail 10.7B v1 GGUF?

The files are on Hugging Face in the andrijdavid/LMCocktail-10.7B-v1-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 LMCocktail 10.7B v1 use?

Hugging Face lists the license as llama2. 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 andrijdavid

All by andrijdavid →

More Lmcocktail models

All Lmcocktail →

Other medium models

All medium models →