ST

Starlight Pro 1

StarlightGGUF by mradermacherUpdated 2026-10-18
Download on Hugging Face
Parameters1.88B
Context256K
Layers24
Architectureqwen35
Smallest quant1.0 GB
Quick answer

Starlight Pro 1 needs about 2.2 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 12 quants, from 1.0 GB (Q2_K) to 3.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Starlight Pro 1 – a 1.88B Qwen3.5‑based model with agent‑memory

Starlight Pro 1 is a 1.88B parameter Qwen3.5 model with a causal agent‑memory register after each full‑attention layer. It is trained on 262144 context tokens and licensed under apache‑2.0. The model supports reasoning and tool use.

Good at

  • Reasoning
  • Tool integration
  • Long‑context handling

Limits

  • No vision support
  • Requires 8k context for estimates
  • No mixture of experts

Best for

  • Chatbots needing reasoning
  • Tool‑enabled assistants
  • Long‑document summarization

Who it’s for. Developers building LLM applications that require reasoning and tool use within a 1.88B parameter budget. The model is suitable for projects that can run on GPUs with at least 8 GB VRAM and support the Qwen3.5 architecture.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.0 GB 1.9 GB
Fits Get file →
Q3_K_S1.0 GB 1.9 GB
Fits Get file →
Q3_K_M1.1 GB 2.0 GB
Fits Get file →
Q3_K_L1.2 GB 2.1 GB
Fits Get file →
IQ4_XS1.2 GB 2.1 GB
Fits Get file →
Q4_K_S1.2 GB 2.1 GB
Fits Get file →
Q4_K_M1.3 GB 2.2 GB
Fits Get file →
Q5_K_S1.4 GB 2.3 GB
Fits Get file →
Q5_K_M1.4 GB 2.3 GB
Fits Get file →
Q6_K1.6 GB 2.5 GB
Fits Get file →
Q8_02.0 GB 2.9 GB
Fits Get file →
F163.8 GB 4.7 GB
Fits Get file →

For 8 GB VRAM use Q4_K_M (1.27 GB file, ~2.2 GB memory). For 12 GB VRAM use Q5_K_M (1.41 GB file, ~2.3 GB memory). For 16 GB VRAM use F16 (3.78 GB file, ~4.7 GB memory).

What GPU do you need for Starlight Pro 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 Q8_0 (2.0 GB file, about 2.9 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.8 GB file, about 4.7 GB in use).

Which Starlight Pro 1 quant should you choose?

Q4_K_M is the usual starting point for Starlight Pro 1: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.0 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 Q2_K at 1.0 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
Parameters1.88B
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
FamilyStarlight
Licenseapache-2.0
Downloads (HF)885
Last updated2026-10-18

Frequently asked questions about Starlight Pro 1

How much VRAM does Starlight Pro 1 need?

About 2.2 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 Starlight Pro 1 on an 8 GB GPU?

Yes, with F16: the 3.8 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Starlight Pro 1 GGUF?

It depends on the quant: Q2_K is 1.0 GB, Q3_K_S is 1.0 GB, Q3_K_M is 1.1 GB, Q3_K_L is 1.2 GB, IQ4_XS is 1.2 GB, Q4_K_S is 1.2 GB and 6 more.

What context length does Starlight Pro 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 Pro 1 GGUF?

The files are on Hugging Face in the mradermacher/starlight-pro-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 Pro 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 Pro 1 on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 2.2 GB memory at 8k context, fitting within 8 GB VRAM.

Does Starlight Pro 1 support vision?

No, the model does not include vision capabilities.

What license applies to Starlight Pro 1?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Starlight models

All Starlight →

Other tiny models

All tiny models →