ST

Starling-LM-7B-alpha

StarlingGGUF by duyntnetUpdated 2024-04-27
Download on Hugging Face
Parameters7.24B
Context8K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

Starling-LM-7B-alpha needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 1.6 GB (IQ1_S) to 7.7 GB (Q8_0).

Starling‑LM‑7B‑alpha – a 7.24B parameter Llama‑style model

Starling‑LM‑7B‑alpha is a 7.24B parameter Llama architecture model trained with a 8192 token context window. It is available in multiple GGUF quantizations and follows the Openchat 3.5 chat template. The model is released under a non‑standard license.

Good at

  • Conversational chat
  • Openchat‑style prompts
  • Large context handling

Limits

  • No vision support
  • Requires 8192 token context
  • License not standard

Best for

  • Chatbot prototypes
  • Text generation with long context
  • Openchat‑compatible applications

Who it’s for. Developers building chat interfaces that need a 7B‑size model with a large context window. The model is suitable for users who can follow the Openchat 3.5 template and who have the necessary GPU memory for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 3.2 GB
Fits Get file →
IQ1_M1.8 GB 3.3 GB
Fits Get file →
IQ2_XXS2.0 GB 3.6 GB
Fits Get file →
IQ2_XS2.2 GB 3.8 GB
Fits Get file →
IQ2_S2.3 GB 3.9 GB
Fits Get file →
IQ2_M2.5 GB 4.1 GB
Fits Get file →
Q2_K_S2.5 GB 4.1 GB
Fits Get file →
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XXS2.8 GB 4.4 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
IQ4_XS3.9 GB 5.5 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
IQ4_NL4.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_05.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.61 GB, 3.2 GB memory) or IQ1_M (1.75 GB, 3.3 GB memory). For 12 GB VRAM, Q2_K (2.72 GB, 4.3 GB memory) or Q3_K_S (3.16 GB, 4.7 GB memory) are suitable. For 16 GB VRAM, Q4_K_M (4.37 GB, 5.9 GB memory) or Q5_K_S (5 GB, 6.6 GB memory) provide a balance between quality and memory usage.

What GPU do you need for Starling-LM-7B-alpha?

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 IQ2_S (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which Starling-LM-7B-alpha quant should you choose?

Q4_K_M is the usual starting point for Starling-LM-7B-alpha: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 GB, about 1.8 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 IQ1_S at 1.6 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
Parameters7.24B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byduyntnet
FamilyStarling
Licenseother
Downloads (HF)1,054
Last updated2024-04-27

Frequently asked questions about Starling-LM-7B-alpha

How much VRAM does Starling-LM-7B-alpha need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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-LM-7B-alpha on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Starling-LM-7B-alpha GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB and 19 more.

What context length does Starling-LM-7B-alpha support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Starling-LM-7B-alpha GGUF?

The files are on Hugging Face in the duyntnet/Starling-LM-7B-alpha-imatrix-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-LM-7B-alpha use?

Hugging Face lists the license as other. 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‑LM‑7B‑alpha on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quantization. They require about 3.2–3.3 GB of VRAM at 8192 context.

Does the model support image inputs?

No, the model has no vision capabilities.

What chat template should I use?

Use the exact Openchat 3.5 chat template to avoid performance degradation.

Similar models

Browse all →

More from duyntnet

All by duyntnet →

More Starling models

All Starling →

Other small models

All small models →