DI

DiscoLM 120b

DiscolmGGUF by TheBlokeUpdated 2023-12-02
Download on Hugging Face
Parameters118B
Context4K
Layers137
Architecturellama
Smallest quant49.6 GB
Quick answer

DiscoLM 120b needs about 54.7 GB of memory at Q2_K (a 49.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds.

DiscoLM 120b is a 118B-parameter Discolm model in GGUF format, quantized by TheBloke. Its trained context length is 4K tokens. The repository has 1 quant file, from 49.6 GB (Q2_K) to 49.6 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K49.6 GB 52.4 GB
Too big Get file →

What GPU do you need for DiscoLM 120b?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which DiscoLM 120b quant should you choose?

Q2_K (49.6 GB) is the middle option in this repository. 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

Architecturellama
Parameters118B
Layers137
Trained context4,096 tokens
KV cache (fp16)548 KB per token

Source

Quantized byTheBloke
FamilyDiscolm
Licensellama2
Downloads (HF)150
Last updated2023-12-02

Frequently asked questions about DiscoLM 120b

How much VRAM does DiscoLM 120b need?

About 54.7 GB at Q2_K with an 8K context window. That is the 49.6 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 DiscoLM 120b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 54.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DiscoLM 120b GGUF?

It depends on the quant: Q2_K is 49.6 GB.

What context length does DiscoLM 120b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.6 GB at 8K and 2.3 GB at 4K.

Where can I download DiscoLM 120b GGUF?

The files are on Hugging Face in the TheBloke/DiscoLM-120b-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 DiscoLM 120b 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 TheBloke

All by TheBloke →

More Discolm models

All Discolm →

Other large models

All large models →