QW

SauerkrautLM-Qwen-32b

QwenGGUF by redponikeUpdated 2024-07-01
Download on Hugging Face
Parameters32.5B
Context32K
Layers64
Architectureqwen2
Smallest quant14.3 GB
Quick answer

SauerkrautLM-Qwen-32b needs about 22.3 GB of memory at Q4_K_M (a 19.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 14.3 GB (Q3_K_S) to 23.1 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

SauerkrautLM-Qwen-32b is a 32.5B-parameter Qwen model in GGUF format, quantized by redponike. Its trained context length is 32K tokens. The repository has 7 quant files, from 14.3 GB (Q3_K_S) to 23.1 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S14.3 GB 16.9 GB
Too big Get file →
Q3_K_M15.8 GB 18.5 GB
Too big Get file →
Q3_K_L17.1 GB 19.8 GB
Too big Get file →
Q4_K_S18.6 GB 21.3 GB
Too big Get file →
Q4_K_M19.7 GB 22.3 GB
Too big Get file →
Q5_K_S22.5 GB 25.1 GB
Too big Get file →
Q5_K_M23.1 GB 25.7 GB
Too big Get file →

What GPU do you need for SauerkrautLM-Qwen-32b?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.7 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (23.1 GB file, about 25.7 GB in use).

Which SauerkrautLM-Qwen-32b quant should you choose?

Q4_K_M is the usual starting point for SauerkrautLM-Qwen-32b: it balances file size and quality well. Here it is a 19.7 GB file.

If memory is tight, the smallest file is Q3_K_S at 14.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters32.5B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized byredponike
FamilyQwen
Downloads (HF)269
Last updated2024-07-01

Frequently asked questions about SauerkrautLM-Qwen-32b

How much VRAM does SauerkrautLM-Qwen-32b need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 19.7 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 SauerkrautLM-Qwen-32b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SauerkrautLM-Qwen-32b GGUF?

It depends on the quant: Q3_K_S is 14.3 GB, Q3_K_M is 15.8 GB, Q3_K_L is 17.1 GB, Q4_K_S is 18.6 GB, Q4_K_M is 19.7 GB, Q5_K_S is 22.5 GB and 1 more.

What context length does SauerkrautLM-Qwen-32b support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download SauerkrautLM-Qwen-32b GGUF?

The files are on Hugging Face in the redponike/SauerkrautLM-Qwen-32b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from redponike

All by redponike →

More Qwen models

All Qwen →

Other medium models

All medium models →