ZE

Zephyr-3.43B

ZephyrGGUF by afridevaUpdated 2023-12-16
Download on Hugging Face
Parameters3.43B
Context4K
Layers40
Architecturestablelm
Smallest quant1.5 GB
Quick answer

Zephyr-3.43B needs about 5.9 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 1.5 GB (Q2_K) to 6.9 GB.

Zephyr-3.43B: 3.43B parameter stablelm model in GGUF format

Zephyr-3.43B merges 28 layers of Zephyr with 12 layers of Astridboros, totaling 40 layers and 3.43B parameters. It is available in multiple GGUF quantizations from afrideva. The model supports a 4096 token context window.

Good at

  • Stablelm architecture
  • Large context handling
  • Fusion of Zephyr and Astridboros

Limits

  • No vision support
  • License is other, not specified
  • Requires 8k context for memory estimates

Best for

  • Chat applications
  • Text generation
  • Prompt engineering

Who it’s for. Developers needing a stablelm-based model with moderate size and multiple quant options. Suitable for projects that can accommodate the 3.43B parameter count and the 4096 token context.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.5 GB 3.6 GB
Fits Get file →
Q3_K_M1.7 GB 3.9 GB
Fits Get file →
Q4_K_M2.1 GB 4.3 GB
Fits Get file →
Q5_K_M2.4 GB 4.6 GB
Fits Get file →
Q6_K2.8 GB 5.0 GB
Fits Get file →
Q8_03.6 GB 5.8 GB
Fits Get file →
—6.9 GB 9.0 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (1.46 GB, 5.3 GB memory) or Q3_K_M (1.7 GB, 5.6 GB memory). If 12 GB VRAM is available, Q4_K_M (2.09 GB, 5.9 GB memory) or Q5_K_M (2.44 GB, 6.3 GB memory) are suitable. Higher quants increase accuracy but require more memory.

What GPU do you need for Zephyr-3.43B?

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: the best quant that fits is Q4_K_M (2.1 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (6.9 GB file, about 10.7 GB in use).

Which Zephyr-3.43B quant should you choose?

Q4_K_M is the usual starting point for Zephyr-3.43B: it balances file size and quality well. Here it is a 2.1 GB file.

The Q8_0 file is 3.6 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 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

Architecturestablelm
Parameters3.43B
Layers40
Trained context4,096 tokens
KV cache (fp16)400 KB per token

Source

Quantized byafrideva
FamilyZephyr
Licenseother
Downloads (HF)646
Last updated2023-12-16

Frequently asked questions about Zephyr-3.43B

How much VRAM does Zephyr-3.43B need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 2.1 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 Zephyr-3.43B on an 8 GB GPU?

Yes, with Q8_0: the 3.6 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 Zephyr-3.43B GGUF?

It depends on the quant: Q2_K is 1.5 GB, Q3_K_M is 1.7 GB, Q4_K_M is 2.1 GB, Q5_K_M is 2.4 GB, Q6_K is 2.8 GB, Q8_0 is 3.6 GB and 1 more.

What context length does Zephyr-3.43B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.4 GB at 8K and 1.7 GB at 4K.

Where can I download Zephyr-3.43B GGUF?

The files are on Hugging Face in the afrideva/Zephyr-3.43B-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 Zephyr-3.43B 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 Zephyr-3.43B on 8 GB VRAM?

Yes, using Q2_K or Q3_K_M quantizations, which estimate 5.3–5.6 GB memory at 8k context.

Does this model support image inputs?

No, it does not have vision capabilities.

What prompt format is recommended?

Use the Zephyr prompt format as suggested in the model card.

Similar models

Browse all →

More from afrideva

All by afrideva →

More Zephyr models

All Zephyr →

Other tiny models

All tiny models →