SO

sanjiwatsuki_sonya-7b

SonyaGGUF by TheBlokeUpdated 2023-12-31
Download on Hugging Face
Parameters7.24B
Context8K
Layers32
Architecturellama
Smallest quant3.1 GB
Quick answer

sanjiwatsuki_sonya-7b 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 12 quants, from 3.1 GB (Q2_K) to 7.7 GB (Q8_0).

Sonya-7B: 7.24B parameter Llama model optimized for MT‑Bench

Sonya-7B is a 7.24B parameter Llama model with an 8192 token context window. It is a merge of several Alpaca‑formatted models and performs strongly on MT‑Bench. The model is released under a cc‑by‑4.0 license.

Good at

  • Strong MT‑Bench performance
  • Alpaca prompt compatibility
  • Versatile assistant and role‑play tasks

Limits

  • No vision support
  • Requires 8192 context window for best results
  • Quirky outputs due to merge

Best for

  • Chat assistants
  • Creative writing
  • Role‑play scenarios

Who it’s for. Developers and researchers looking for a high‑quality 7B Llama model that excels on MT‑Bench. The model is suitable for local deployment with llama.cpp or compatible GUIs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 4.7 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 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 →
Q4_04.1 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_05.0 GB 6.6 GB
Fits Get file →
Q5_K_S5.0 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 Q4_K or Q4_K_S (≈5.7 GB memory at 8k context). For 12 GB VRAM, Q5_K_M or Q5_K_S (≈6.7 GB). For 16 GB VRAM, Q6_K (≈7.5 GB).

What GPU do you need for sanjiwatsuki_sonya-7b?

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 (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 sanjiwatsuki_sonya-7b quant should you choose?

Q4_K_M is the usual starting point for sanjiwatsuki_sonya-7b: 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 Q2_K at 3.1 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 byTheBloke
FamilySonya
Licensecc-by-4.0
Downloads (HF)983
Last updated2023-12-31

Frequently asked questions about sanjiwatsuki_sonya-7b

How much VRAM does sanjiwatsuki_sonya-7b 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 sanjiwatsuki_sonya-7b 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 sanjiwatsuki_sonya-7b GGUF?

It depends on the quant: Q2_K is 3.1 GB, Q3_K_S is 3.2 GB, Q3_K_M is 3.5 GB, Q3_K_L is 3.8 GB, Q4_0 is 4.1 GB, Q4_K_S is 4.1 GB and 6 more.

What context length does sanjiwatsuki_sonya-7b 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 sanjiwatsuki_sonya-7b GGUF?

The files are on Hugging Face in the TheBloke/Sonya-7B-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 sanjiwatsuki_sonya-7b use?

Hugging Face lists the license as cc-by-4.0. 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 Sonya-7B on 8 GB VRAM?

Yes, use Q4_K or Q4_K_S quantization, which require about 5.7 GB memory at 8k context.

Does Sonya-7B support vision tasks?

No, the model has no vision capabilities.

What prompt format works best?

Alpaca prompt format is recommended for optimal performance.

Other GGUFs of Sonya-7B

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Sonya models

All Sonya →

Other small models

All small models →