SY

Kysun63__Synllama 1b Reproduced

SynllamaGGUF by lukaskimUpdated 2026-06-18
Download on Hugging Face
Parameters1.5B
Context128K
Layers16
Architecturellama
Smallest quant0.7 GB
Quick answer

Kysun63__Synllama 1b Reproduced needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.7 GB (Q2_K) to 3.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

Kysun63__Synllama 1b Reproduced is a 1.5B-parameter Synllama model in GGUF format, quantized by lukaskim. Its trained context length is 128K tokens. The repository has 5 quant files, from 0.7 GB (Q2_K) to 3.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.7 GB 1.4 GB
Fits Get file →
Q4_K_M1.0 GB 1.7 GB
Fits Get file →
Q6_K1.2 GB 2.0 GB
Fits Get file →
Q8_01.6 GB 2.4 GB
Fits Get file →
F163.0 GB 3.8 GB
Fits Get file →

What GPU do you need for Kysun63__Synllama 1b Reproduced?

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 F16 (3.0 GB file, about 3.8 GB in use).

Which Kysun63__Synllama 1b Reproduced quant should you choose?

Q4_K_M is the usual starting point for Kysun63__Synllama 1b Reproduced: it balances file size and quality well. Here it is a 1.0 GB file.

The Q8_0 file is 1.6 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 Q2_K at 0.7 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
Parameters1.5B
Layers16
Trained context131,072 tokens
KV cache (fp16)32 KB per token

Source

Quantized bylukaskim
FamilySynllama
Licensellama3.2
Downloads (HF)116
Last updated2026-06-18

Frequently asked questions about Kysun63__Synllama 1b Reproduced

How much VRAM does Kysun63__Synllama 1b Reproduced need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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 Kysun63__Synllama 1b Reproduced on an 8 GB GPU?

Yes, with F16: the 3.0 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kysun63__Synllama 1b Reproduced GGUF?

It depends on the quant: Q2_K is 0.7 GB, Q4_K_M is 1.0 GB, Q6_K is 1.2 GB, Q8_0 is 1.6 GB, F16 is 3.0 GB.

What context length does Kysun63__Synllama 1b Reproduced support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download Kysun63__Synllama 1b Reproduced GGUF?

The files are on Hugging Face in the lukaskim/SynLlama-1B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Kysun63__Synllama 1b Reproduced use?

Hugging Face lists the license as llama3.2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from lukaskim

All by lukaskim →

Other tiny models

All tiny models →