TM

tmp

TmpGGUF by josephiloUpdated 2024-03-11
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant16.7 GB
Quick answer

tmp needs about 19.2 GB of memory at Q3_K_M (a 16.7 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 8.1 GB.

tmp is a 34.4B-parameter Tmp model in GGUF format, quantized by josephilo. Its trained context length is 195K tokens. The repository has 1 quant file, from 16.7 GB (Q3_K_M) to 16.7 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M16.7 GB 19.2 GB
Too big Get file →

What GPU do you need for tmp?

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 Q3_K_M (16.7 GB file, about 19.2 GB in use).

Which tmp quant should you choose?

Q3_K_M (16.7 GB) is the middle option in this repository. 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
Parameters34.4B
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized byjosephilo
FamilyTmp
Repositoryjosephilo/tmp
Downloads (HF)3
Last updated2024-03-11

Frequently asked questions about tmp

How much VRAM does tmp need?

About 19.2 GB at Q3_K_M with an 8K context window. That is the 16.7 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 tmp on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of tmp GGUF?

It depends on the quant: Q3_K_M is 16.7 GB.

What context length does tmp support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download tmp GGUF?

The files are on Hugging Face in the josephilo/tmp 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 Tmp models

All Tmp →

Other large models

All large models →