RE

recursechat

RecursechatGGUF by recursechatUpdated 2024-09-27
Download on Hugging Face
Parameters109M
Context128K
Layers28
Architecturellama
Smallest quant0.4 GB
Quick answer

recursechat needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.4 GB (F32) to 5.8 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

recursechat is a 109M-parameter Recursechat model in GGUF format, quantized by recursechat. Its trained context length is 128K tokens. The repository has 12 quant files, from 0.4 GB (F32) to 5.8 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F320.4 GB 1.9 GB
Fits Get file →
F320.5 GB 2.0 GB
Fits Get file →
Q8_01.3 GB 2.8 GB
Fits Get file →
Q4_K_M2.0 GB 3.5 GB
Fits Get file →
Q8_03.4 GB 4.9 GB
Fits Get file →
Q5_K_M5.1 GB 6.6 GB
Fits Get file →
—5.1 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.6 GB
Fits Get file →
Q5_K_M5.7 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.2 GB
Fits Get file →
Q4_K_M5.8 GB 7.2 GB
Tight Get file →

What GPU do you need for recursechat?

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: the best quant that fits is Q4_K_M (2.0 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (5.8 GB file, about 7.2 GB in use).

Which recursechat quant should you choose?

Q4_K_M is the usual starting point for recursechat: it balances file size and quality well. Here it is a 2.0 GB file.

The Q8_0 file is 1.3 GB, about 0.7 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 F32 at 0.4 GB, with the quality trade-offs that come with fewer bits. 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
Parameters109M
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byrecursechat
Downloads (HF)71
Last updated2024-09-27

Frequently asked questions about recursechat

How much VRAM does recursechat need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 recursechat on an 8 GB GPU?

Yes, with Q4_K_M: the 5.8 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of recursechat GGUF?

It depends on the quant: F32 is 0.4 GB, F32 is 0.5 GB, Q8_0 is 1.3 GB, Q4_K_M is 2.0 GB, Q8_0 is 3.4 GB, Q5_K_M is 5.1 GB and 6 more.

What context length does recursechat support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download recursechat GGUF?

The files are on Hugging Face in the recursechat/recursechat 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 recursechat

All by recursechat →

Other tiny models

All tiny models →