LW

LWM Text 1M mpe32k

LwmGGUF by emozillaUpdated 2024-03-05
Download on Hugging Face
Parameters6.74B
Context1024K
Layers32
Architecturellama
Smallest quant13.5 GB
Quick answer

LWM Text 1M mpe32k needs about 18.3 GB of memory at F16 (a 13.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

LWM Text 1M mpe32k is a 6.74B-parameter Lwm model in GGUF format, quantized by emozilla. Its trained context length is 1024K tokens. The repository has 1 quant file, from 13.5 GB (F16) to 13.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1613.5 GB 18.3 GB
Too big Get file →

What GPU do you need for LWM Text 1M mpe32k?

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: the best quant that fits is F16 (13.5 GB file, about 18.3 GB in use).

Which LWM Text 1M mpe32k quant should you choose?

F16 (13.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context1,048,576 tokens
KV cache (fp16)512 KB per token

Source

Quantized byemozilla
FamilyLwm
Downloads (HF)20
Last updated2024-03-05

Frequently asked questions about LWM Text 1M mpe32k

How much VRAM does LWM Text 1M mpe32k need?

About 18.3 GB at F16 with an 8K context window. That is the 13.5 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 LWM Text 1M mpe32k on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LWM Text 1M mpe32k GGUF?

It depends on the quant: F16 is 13.5 GB.

What context length does LWM Text 1M mpe32k support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download LWM Text 1M mpe32k GGUF?

The files are on Hugging Face in the emozilla/LWM-Text-1M-mpe32k 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 emozilla

All by emozilla →

More Lwm models

All Lwm →

Other small models

All small models →