LW

LWM Text Chat 512K

LwmGGUF by noldUpdated 2024-02-14
Download on Hugging Face
Parameters6.74B
Context512K
Layers32
Architecturellama
Smallest quant2.5 GB
Quick answer

LWM Text Chat 512K needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 2.5 GB (Q2_K) to 7.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

LWM Text Chat 512K is a 6.74B-parameter Lwm model in GGUF format, quantized by nold. Its trained context length is 512K tokens. The repository has 5 quant files, from 2.5 GB (Q2_K) to 7.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 7.3 GB
Tight Get file →
Q4_K_M4.1 GB 8.9 GB
Too big Get file →
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →

What GPU do you need for LWM Text Chat 512K?

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: the best quant that fits is Q2_K (2.5 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which LWM Text Chat 512K quant should you choose?

Q4_K_M is the usual starting point for LWM Text Chat 512K: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 Q2_K at 2.5 GB, with the quality trade-offs that come with fewer bits. 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
Parameters6.74B
Layers32
Trained context524,288 tokens
KV cache (fp16)512 KB per token

Source

Quantized bynold
FamilyLwm
Downloads (HF)35
Last updated2024-02-14

Frequently asked questions about LWM Text Chat 512K

How much VRAM does LWM Text Chat 512K need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 Chat 512K on an 8 GB GPU?

Yes, with Q2_K: the 2.5 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LWM Text Chat 512K GGUF?

It depends on the quant: Q2_K is 2.5 GB, Q4_K_M is 4.1 GB, Q5_K_M is 4.8 GB, Q6_K is 5.5 GB, Q8_0 is 7.2 GB.

What context length does LWM Text Chat 512K support?

The GGUF header lists a trained context length of 524,288 tokens (512K). 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 Chat 512K GGUF?

The files are on Hugging Face in the nold/LWM-Text-Chat-512K-GGUF 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 nold

All by nold →

More Lwm models

All Lwm →

Other small models

All small models →