ST

Starlight Small 1

StarlightGGUF by mradermacherUpdated 2026-10-18
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.4 GB
Quick answer

Starlight Small 1 needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.4 GB (Q2_K) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Starlight Small 1 – 0.752B Qwen3.5‑based model with agent register

Starlight Small 1 is a 0.752B parameter model built on the Qwen3.5 architecture. It includes a causal agent‑memory register after each full‑attention layer. The model is trained on a context of 262144 tokens and released under Apache‑2.0.

Good at

  • Reasoning
  • Tool usage
  • Causal agent memory

Limits

  • No vision support
  • Context limited to 262144 tokens
  • Requires 8‑bit or higher VRAM for full performance

Best for

  • Local inference on modest GPUs
  • Rapid prototyping of agentic workflows
  • Educational demonstrations of Qwen3.5 architecture

Who it’s for. Developers and researchers who need a lightweight, open‑source Qwen3.5 variant with agent memory. The model is suitable for local deployment and experimentation without large GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 1.3 GB
Fits Get file →
Q3_K_S0.4 GB 1.3 GB
Fits Get file →
Q3_K_M0.5 GB 1.4 GB
Fits Get file →
Q3_K_L0.5 GB 1.4 GB
Fits Get file →
Q4_K_S0.5 GB 1.4 GB
Fits Get file →
IQ4_XS0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q5_K_S0.6 GB 1.5 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.5 GB
Fits Get file →
Q8_00.8 GB 1.7 GB
Fits Get file →
F161.5 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, use Q2_K (0.42 GB file, ~1.3 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (0.53 GB file, ~1.4 GB memory) or Q5_K_S (0.56 GB file, ~1.5 GB memory). Higher precision quants increase accuracy but need more memory.

What GPU do you need for Starlight Small 1?

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 (1.5 GB file, about 2.4 GB in use).

Which Starlight Small 1 quant should you choose?

Q4_K_M is the usual starting point for Starlight Small 1: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.5 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 0.4 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

Architectureqwen35
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
FamilyStarlight
Licenseapache-2.0
Downloads (HF)871
Last updated2026-10-18

Frequently asked questions about Starlight Small 1

How much VRAM does Starlight Small 1 need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 Starlight Small 1 on an 8 GB GPU?

Yes, with F16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Starlight Small 1 GGUF?

It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, Q4_K_S is 0.5 GB, IQ4_XS is 0.5 GB and 6 more.

What context length does Starlight Small 1 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download Starlight Small 1 GGUF?

The files are on Hugging Face in the mradermacher/starlight-small-1-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 Starlight Small 1 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Starlight Small 1 on 8 GB VRAM?

Yes, the Q2_K quant uses 0.42 GB file size and requires about 1.3 GB VRAM at 8 k context, which fits within 8 GB. Higher quants may exceed the limit.

Does Starlight Small 1 support vision?

No, the model has no vision capabilities. It is a text‑only model.

What is the maximum context length?

The model is trained on 262144 tokens and can handle up to that many tokens in context.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Starlight models

All Starlight →

Other tiny models

All tiny models →