ST

starling 7B i1

StarlingGGUF by mradermacherUpdated 2024-12-03
Download on Hugging Face
Parameters6.74B
Context2K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

starling 7B i1 needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.5 GB (IQ1_S) to 5.5 GB (Q6_K).

Starling 7B i1 – a safety‑aligned Llama‑based model

Starling 7B i1 is a 6.74 billion‑parameter Llama model fine‑tuned for safety. It was trained on HarmfulQA and shows reduced attack success rates compared to Vicuna. The model is released under Apache‑2.0.

Good at

  • Safety‑aligned responses
  • Reduced attack success rate
  • Improved HHH score

Limits

  • No vision support
  • Limited to 2048 context tokens
  • No mixture of experts

Best for

  • Chat applications needing safer outputs
  • Red‑team testing
  • Safety‑benchmark research

Who it’s for. Developers and researchers who need a Llama‑based model with enhanced safety characteristics. The model is suitable for applications where reduced harmful content is critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.5 GB 3.1 GB
Fits Get file →
IQ1_M1.7 GB 3.2 GB
Fits Get file →
IQ2_XXS1.9 GB 3.4 GB
Fits Get file →
IQ2_XS2.0 GB 3.6 GB
Fits Get file →
IQ2_S2.2 GB 3.8 GB
Fits Get file →
IQ2_M2.4 GB 3.9 GB
Fits Get file →
Q2_K2.5 GB 4.1 GB
Fits Get file →
IQ3_XXS2.6 GB 4.2 GB
Fits Get file →
IQ3_XS2.8 GB 4.4 GB
Fits Get file →
IQ3_S2.9 GB 4.5 GB
Fits Get file →
Q3_K_S2.9 GB 4.5 GB
Fits Get file →
IQ3_M3.1 GB 4.7 GB
Fits Get file →
Q3_K_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_L3.6 GB 5.2 GB
Fits Get file →
IQ4_XS3.6 GB 5.2 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
Q4_03.8 GB 5.4 GB
Fits Get file →
Q4_K_S3.9 GB 5.4 GB
Fits Get file →
Q4_K_M4.1 GB 5.7 GB
Fits Get file →
Q5_K_S4.7 GB 6.2 GB
Fits Get file →
Q5_K_M4.8 GB 6.4 GB
Fits Get file →
Q6_K5.5 GB 7.1 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (1.53 GB, 6.3 GB memory) or IQ1_M (1.65 GB, 6.4 GB memory). If 12 GB VRAM is available, Q4_K_M (4.08 GB, 8.9 GB memory) offers higher quality. Larger GPUs can run Q5_K_M or Q6_K for best performance.

What GPU do you need for starling 7B i1?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 10.3 GB in use).

Which starling 7B i1 quant should you choose?

Q4_K_M is the usual starting point for starling 7B i1: it balances file size and quality well. Here it is a 4.1 GB file.

If memory is tight, the smallest file is IQ1_S at 1.5 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
Parameters6.74B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyStarling
Licenseapache-2.0
Downloads (HF)616
Last updated2024-12-03

Frequently asked questions about starling 7B i1

How much VRAM does starling 7B i1 need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 starling 7B i1 on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of starling 7B i1 GGUF?

It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.2 GB, IQ2_M is 2.4 GB and 18 more.

What context length does starling 7B i1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download starling 7B i1 GGUF?

The files are on Hugging Face in the mradermacher/starling-7B-i1-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 starling 7B i1 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 Starling 7B i1 on 8 GB VRAM?

Yes, the IQ1_S and IQ1_M quantizations fit within 8 GB VRAM, using approximately 6.3–6.4 GB of memory at 8k context.

Does Starling 7B i1 support vision?

No, the model has no vision capabilities.

What license applies to Starling 7B i1?

The model is released under the Apache‑2.0 license.

Other GGUFs of starling-7B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Starling models

All Starling →

Other small models

All small models →