AT

Atlas Chat 27B

AtlasGGUF by RichardErkhovUpdated 2024-10-30
Download on Hugging Face
Parameters27.2B
Context8K
Layers46
Architecturegemma2
Smallest quant1.3 GB
Quick answer

Atlas Chat 27B needs about 20.2 GB of memory at Q4_K_M (a 16.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 19 quants, from 1.3 GB (Q3_K_S) to 28.9 GB (Q8_0).

Atlas Chat 27B is a 27.2B-parameter Atlas model in GGUF format, quantized by RichardErkhov. Its trained context length is 8K tokens. The repository has 19 quant files, from 1.3 GB (Q3_K_S) to 28.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S1.3 GB 4.8 GB
Fits Get file →
Q3_K6.0 GB 9.6 GB
Too big Get file →
Q3_K_M7.0 GB 10.6 GB
Too big Get file →
Q2_K10.4 GB 14.0 GB
Too big Get file →
Q3_K_L14.5 GB 18.1 GB
Too big Get file →
IQ4_XS14.9 GB 18.5 GB
Too big Get file →
Q4_015.6 GB 19.2 GB
Too big Get file →
IQ4_NL15.7 GB 19.3 GB
Too big Get file →
Q4_K_S15.7 GB 19.3 GB
Too big Get file →
Q4_K16.6 GB 20.2 GB
Too big Get file →
Q4_K_M16.6 GB 20.2 GB
Too big Get file →
Q4_117.3 GB 20.8 GB
Too big Get file →
Q5_018.9 GB 22.5 GB
Too big Get file →
Q5_K_S18.9 GB 22.5 GB
Too big Get file →
Q5_K19.4 GB 23.0 GB
Too big Get file →
Q5_K_M19.4 GB 23.0 GB
Too big Get file →
Q5_120.5 GB 24.1 GB
Too big Get file →
Q6_K22.3 GB 25.9 GB
Too big Get file →
Q8_028.9 GB 32.5 GB
Too big Get file →

What GPU do you need for Atlas Chat 27B?

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_S (1.3 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_S (1.3 GB file, about 4.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_M (7.0 GB file, about 10.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (10.4 GB file, about 14.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K (19.4 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.3 GB file, about 25.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.9 GB file, about 32.5 GB in use).

Which Atlas Chat 27B quant should you choose?

Q4_K_M is the usual starting point for Atlas Chat 27B: it balances file size and quality well. Here it is a 16.6 GB file.

The Q8_0 file is 28.9 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 Q3_K_S at 1.3 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

Architecturegemma2
Parameters27.2B
Layers46
Trained context8,192 tokens
KV cache (fp16)368 KB per token

Source

Quantized byRichardErkhov
FamilyAtlas
Licensegemma
Downloads (HF)253
Last updated2024-10-30

Frequently asked questions about Atlas Chat 27B

How much VRAM does Atlas Chat 27B need?

About 20.2 GB at Q4_K_M with an 8K context window. That is the 16.6 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 Atlas Chat 27B on an 8 GB GPU?

Yes, with Q3_K_S: the 1.3 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Atlas Chat 27B GGUF?

It depends on the quant: Q3_K_S is 1.3 GB, Q3_K is 6.0 GB, Q3_K_M is 7.0 GB, Q2_K is 10.4 GB, Q3_K_L is 14.5 GB, IQ4_XS is 14.9 GB and 13 more.

What context length does Atlas Chat 27B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.1 GB at 8K and 3.1 GB at 8K.

Where can I download Atlas Chat 27B GGUF?

The files are on Hugging Face in the RichardErkhov/MBZUAI-Paris_-_Atlas-Chat-27B-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 Atlas Chat 27B use?

Hugging Face lists the license as gemma. 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 Atlas models

All Atlas →

Other medium models

All medium models →