CH

chihoonlee10 T3Q Merge SOLAR12

ChihoonleeGGUF by RichardErkhovUpdated 2024-11-07
Download on Hugging Face
Parameters10.9B
Context4K
Layers48
Architecturellama
Smallest quant3.7 GB
Quick answer

chihoonlee10 T3Q Merge SOLAR12 needs about 8.7 GB of memory at Q4_K_M (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 19 quants, from 3.7 GB (Q3_K_L) to 11.5 GB (Q8_0).

chihoonlee10 T3Q Merge SOLAR12 is a 10.9B-parameter Chihoonlee model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 19 quant files, from 3.7 GB (Q3_K_L) to 11.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L3.7 GB 5.0 GB
Fits Get file →
Q2_K4.1 GB 5.4 GB
Fits Get file →
Q3_K_S4.7 GB 6.1 GB
Fits Get file →
Q3_K5.3 GB 6.6 GB
Fits Get file →
Q3_K_M5.3 GB 6.6 GB
Fits Get file →
IQ4_XS5.9 GB 7.2 GB
Tight Get file →
Q4_06.2 GB 7.5 GB
Tight Get file →
Q4_K_S6.2 GB 7.5 GB
Tight Get file →
IQ4_NL6.2 GB 7.5 GB
Tight Get file →
Q4_K6.6 GB 7.9 GB
Tight Get file →
Q4_K_M6.6 GB 7.9 GB
Tight Get file →
Q4_16.8 GB 8.1 GB
Too big Get file →
Q5_07.5 GB 8.8 GB
Too big Get file →
Q5_K_S7.5 GB 8.8 GB
Too big Get file →
Q5_K7.7 GB 9.0 GB
Too big Get file →
Q5_K_M7.7 GB 9.0 GB
Too big Get file →
Q5_18.2 GB 9.5 GB
Too big Get file →
Q6_K8.9 GB 10.2 GB
Too big Get file →
Q8_011.5 GB 12.8 GB
Too big Get file →

What GPU do you need for chihoonlee10 T3Q Merge SOLAR12?

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 Q3_K_L (3.7 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ4_XS (5.9 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.9 GB file, about 11.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.5 GB file, about 13.7 GB in use).

Which chihoonlee10 T3Q Merge SOLAR12 quant should you choose?

Q4_K_M is the usual starting point for chihoonlee10 T3Q Merge SOLAR12: it balances file size and quality well. Here it is a 6.6 GB file.

The Q8_0 file is 11.5 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 Q3_K_L at 3.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.9B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized byRichardErkhov
Licenseapache-2.0
Downloads (HF)2
Last updated2024-11-07

Frequently asked questions about chihoonlee10 T3Q Merge SOLAR12

How much VRAM does chihoonlee10 T3Q Merge SOLAR12 need?

About 8.7 GB at Q4_K_M with an 8K context window. That is the 6.6 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 chihoonlee10 T3Q Merge SOLAR12 on an 8 GB GPU?

Yes, with IQ4_XS: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of chihoonlee10 T3Q Merge SOLAR12 GGUF?

It depends on the quant: Q3_K_L is 3.7 GB, Q2_K is 4.1 GB, Q3_K_S is 4.7 GB, Q3_K is 5.3 GB, Q3_K_M is 5.3 GB, IQ4_XS is 5.9 GB and 13 more.

What context length does chihoonlee10 T3Q Merge SOLAR12 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 chihoonlee10 T3Q Merge SOLAR12 GGUF?

The files are on Hugging Face in the RichardErkhov/chihoonlee10_-_T3Q-Merge-SOLAR12-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 chihoonlee10 T3Q Merge SOLAR12 use?

Hugging Face lists the license as apache-2.0. 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 →

More Chihoonlee models

All Chihoonlee →

Other medium models

All medium models →