SU

SumanthRH OpenRLHF smol sft mixture

SumanthrhGGUF by RichardErkhovUpdated 2024-11-11
Download on Hugging Face
Parameters1.92B
Context8K
Layers4
Architecturellama
Smallest quant0.8 GB
Quick answer

SumanthRH OpenRLHF smol sft mixture needs about 1.9 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.8 GB (Q5_K_S) to 2.1 GB (Q8_0).

SumanthRH OpenRLHF smol sft mixture is a 1.92B-parameter Sumanthrh model in GGUF format, quantized by RichardErkhov. Its trained context length is 8K tokens. The repository has 19 quant files, from 0.8 GB (Q5_K_S) to 2.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S0.8 GB 1.5 GB
Fits Get file →
Q2_K0.9 GB 1.6 GB
Fits Get file →
Q3_K_S1.0 GB 1.7 GB
Fits Get file →
Q3_K1.1 GB 1.7 GB
Fits Get file →
Q3_K_M1.1 GB 1.7 GB
Fits Get file →
Q3_K_L1.1 GB 1.8 GB
Fits Get file →
IQ4_XS1.2 GB 1.8 GB
Fits Get file →
Q4_01.2 GB 1.9 GB
Fits Get file →
IQ4_NL1.2 GB 1.9 GB
Fits Get file →
Q4_K_S1.2 GB 1.9 GB
Fits Get file →
Q4_K1.3 GB 1.9 GB
Fits Get file →
Q4_K_M1.3 GB 1.9 GB
Fits Get file →
Q4_11.3 GB 1.9 GB
Fits Get file →
Q5_01.4 GB 2.0 GB
Fits Get file →
Q5_K1.4 GB 2.1 GB
Fits Get file →
Q5_K_M1.4 GB 2.1 GB
Fits Get file →
Q5_11.5 GB 2.1 GB
Fits Get file →
Q6_K1.6 GB 2.2 GB
Fits Get file →
Q8_02.1 GB 2.7 GB
Fits Get file →

What GPU do you need for SumanthRH OpenRLHF smol sft mixture?

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 Q8_0 (2.1 GB file, about 2.7 GB in use).

Which SumanthRH OpenRLHF smol sft mixture quant should you choose?

Q4_K_M is the usual starting point for SumanthRH OpenRLHF smol sft mixture: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.1 GB, about 1.6 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 Q5_K_S at 0.8 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.92B
Layers4
Trained context8,192 tokens
KV cache (fp16)16 KB per token

Source

Quantized byRichardErkhov
FamilySumanthrh
Downloads (HF)39
Last updated2024-11-11

Frequently asked questions about SumanthRH OpenRLHF smol sft mixture

How much VRAM does SumanthRH OpenRLHF smol sft mixture need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 1.3 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 SumanthRH OpenRLHF smol sft mixture on an 8 GB GPU?

Yes, with Q8_0: the 2.1 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SumanthRH OpenRLHF smol sft mixture GGUF?

It depends on the quant: Q5_K_S is 0.8 GB, Q2_K is 0.9 GB, Q3_K_S is 1.0 GB, Q3_K is 1.1 GB, Q3_K_M is 1.1 GB, Q3_K_L is 1.1 GB and 13 more.

What context length does SumanthRH OpenRLHF smol sft mixture support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.1 GB at 8K.

Where can I download SumanthRH OpenRLHF smol sft mixture GGUF?

The files are on Hugging Face in the RichardErkhov/SumanthRH_-_OpenRLHF-smol-sft-mixture-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 RichardErkhov

All by RichardErkhov →

Other tiny models

All tiny models →