SM

smallstepai Misal 1B base v0.1

SmallstepaiGGUF by RichardErkhovUpdated 2024-10-29
Download on Hugging Face
Parameters1.16B
Context2K
Layers—
Architecturellama
Smallest quant0.4 GB
Quick answer

smallstepai Misal 1B base v0.1 needs about 1.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.4 GB (Q5_K_S) to 1.2 GB (Q8_0).

smallstepai Misal 1B base v0.1 is a 1.16B-parameter Smallstepai model in GGUF format, quantized by RichardErkhov. Its trained context length is 2K tokens. The repository has 19 quant files, from 0.4 GB (Q5_K_S) to 1.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S0.4 GB 0.9 GB
Fits Get file →
Q2_K0.5 GB 1.0 GB
Fits Get file →
Q3_K_S0.5 GB 1.1 GB
Fits Get file →
Q3_K0.6 GB 1.1 GB
Fits Get file →
Q3_K_M0.6 GB 1.1 GB
Fits Get file →
Q3_K_L0.6 GB 1.1 GB
Fits Get file →
IQ4_XS0.7 GB 1.2 GB
Fits Get file →
Q4_00.7 GB 1.2 GB
Fits Get file →
Q4_K_S0.7 GB 1.2 GB
Fits Get file →
IQ4_NL0.7 GB 1.2 GB
Fits Get file →
Q4_K0.7 GB 1.2 GB
Fits Get file →
Q4_K_M0.7 GB 1.2 GB
Fits Get file →
Q4_10.7 GB 1.3 GB
Fits Get file →
Q5_00.8 GB 1.3 GB
Fits Get file →
Q5_K0.8 GB 1.4 GB
Fits Get file →
Q5_K_M0.8 GB 1.4 GB
Fits Get file →
Q5_10.9 GB 1.4 GB
Fits Get file →
Q6_K1.0 GB 1.5 GB
Fits Get file →
Q8_01.2 GB 1.8 GB
Fits Get file →

What GPU do you need for smallstepai Misal 1B base v0.1?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (1.2 GB file, about 1.9 GB in use).

Which smallstepai Misal 1B base v0.1 quant should you choose?

Q4_K_M is the usual starting point for smallstepai Misal 1B base v0.1: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.2 GB, about 1.7 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 Q5_K_S at 0.4 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
Parameters1.16B
Trained context2,048 tokens

Source

Quantized byRichardErkhov
Downloads (HF)18
Last updated2024-10-29

Frequently asked questions about smallstepai Misal 1B base v0.1

How much VRAM does smallstepai Misal 1B base v0.1 need?

About 1.3 GB at Q4_K_M with an 8K context window. That is the 0.7 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 smallstepai Misal 1B base v0.1 on an 8 GB GPU?

Yes, with Q8_0: the 1.2 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of smallstepai Misal 1B base v0.1 GGUF?

It depends on the quant: Q5_K_S is 0.4 GB, Q2_K is 0.5 GB, Q3_K_S is 0.5 GB, Q3_K is 0.6 GB, Q3_K_M is 0.6 GB, Q3_K_L is 0.6 GB and 13 more.

What context length does smallstepai Misal 1B base v0.1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K).

Where can I download smallstepai Misal 1B base v0.1 GGUF?

The files are on Hugging Face in the RichardErkhov/smallstepai_-_Misal-1B-base-v0.1-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 →