FE

FengZheng-7B-Base

FengzhengGGUF by mradermacherUpdated 2024-05-09
Download on Hugging Face
Parameters7.72B
Context32K
Layers32
Architectureqwen2
Smallest quant3.1 GB
Quick answer

FengZheng-7B-Base needs about 9.6 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 15 quants, from 3.1 GB (Q2_K) to 15.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

FengZheng-7B-Base is a 7.72B-parameter Fengzheng model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 15 quant files, from 3.1 GB (Q2_K) to 15.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 7.9 GB
Tight Get file →
IQ3_XS3.4 GB 8.2 GB
Too big Get file →
IQ3_S3.6 GB 8.4 GB
Too big Get file →
Q3_K_S3.6 GB 8.4 GB
Too big Get file →
IQ3_M3.7 GB 8.5 GB
Too big Get file →
Q3_K_M3.9 GB 8.7 GB
Too big Get file →
Q3_K_L4.2 GB 9.0 GB
Too big Get file →
IQ4_XS4.3 GB 9.1 GB
Too big Get file →
Q4_K_S4.5 GB 9.3 GB
Too big Get file →
Q4_K_M4.8 GB 9.6 GB
Too big Get file →
Q5_K_S5.4 GB 10.2 GB
Too big Get file →
Q5_K_M5.5 GB 10.3 GB
Too big Get file →
Q6_K6.3 GB 11.1 GB
Too big Get file →
Q8_08.2 GB 13.0 GB
Too big Get file →
F1615.4 GB 20.2 GB
Too big Get file →

What GPU do you need for FengZheng-7B-Base?

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 Q2_K (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.2 GB file, about 13.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.4 GB file, about 20.2 GB in use).

Which FengZheng-7B-Base quant should you choose?

Q4_K_M is the usual starting point for FengZheng-7B-Base: it balances file size and quality well. Here it is a 4.8 GB file.

The Q8_0 file is 8.2 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 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

Architectureqwen2
Parameters7.72B
Layers32
Trained context32,768 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyFengzheng
Licenseapache-2.0
Downloads (HF)72
Last updated2024-05-09

Frequently asked questions about FengZheng-7B-Base

How much VRAM does FengZheng-7B-Base need?

About 9.6 GB at Q4_K_M with an 8K context window. That is the 4.8 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 FengZheng-7B-Base on an 8 GB GPU?

Yes, with Q2_K: 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 FengZheng-7B-Base GGUF?

It depends on the quant: Q2_K is 3.1 GB, IQ3_XS is 3.4 GB, IQ3_S is 3.6 GB, Q3_K_S is 3.6 GB, IQ3_M is 3.7 GB, Q3_K_M is 3.9 GB and 9 more.

What context length does FengZheng-7B-Base support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download FengZheng-7B-Base GGUF?

The files are on Hugging Face in the mradermacher/FengZheng-7B-Base-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 FengZheng-7B-Base 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.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Fengzheng models

All Fengzheng →

Other small models

All small models →