TE

test cache

TestGGUF by Rpo5777Updated 2026-06-13
Download on Hugging Face
Parameters39.1B
Context256K
Layers—
Architectureqwen35
Smallest quant14.8 GB
Quick answer

test cache needs about 27.7 GB of memory at Q4_K_M (a 24.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 10 quants, from 14.8 GB (IQ2_M) to 42.8 GB (Q8_0).

test cache is a 39.1B-parameter Test model in GGUF format, quantized by Rpo5777. Its trained context length is 256K tokens. The repository has 10 quant files, from 14.8 GB (IQ2_M) to 42.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M14.8 GB 17.0 GB
Too big Get file →
IQ3_M18.4 GB 21.1 GB
Too big Get file →
IQ4_XS22.1 GB 25.2 GB
Too big Get file →
Q4_K_S22.8 GB 26.0 GB
Too big Get file →
IQ4_NL23.1 GB 26.4 GB
Too big Get file →
Q4_K_M24.3 GB 27.7 GB
Too big Get file →
Q5_K_S27.4 GB 31.2 GB
Too big Get file →
Q5_K_M28.2 GB 32.1 GB
Too big Get file →
Q6_K32.4 GB 36.8 GB
Too big Get file →
Q8_042.8 GB 48.5 GB
Too big Get file →

What GPU do you need for test cache?

These figures add the file size, an fp16 KV cache at an 8K context window 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 IQ3_M (18.4 GB file, about 21.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_S (27.4 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (32.4 GB file, about 36.8 GB in use).

Which test cache quant should you choose?

Q4_K_M is the usual starting point for test cache: it balances file size and quality well. Here it is a 24.3 GB file.

The Q8_0 file is 42.8 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 IQ2_M at 14.8 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

Architectureqwen35
Parameters39.1B
Trained context262,144 tokens

Source

Quantized byRpo5777
FamilyTest
Downloads (HF)0
Last updated2026-06-13

Frequently asked questions about test cache

How much VRAM does test cache need?

About 27.7 GB at Q4_K_M with an 8K context window. That is the 24.3 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 test cache on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of test cache GGUF?

It depends on the quant: IQ2_M is 14.8 GB, IQ3_M is 18.4 GB, IQ4_XS is 22.1 GB, Q4_K_S is 22.8 GB, IQ4_NL is 23.1 GB, Q4_K_M is 24.3 GB and 4 more.

What context length does test cache support?

The GGUF header lists a trained context length of 262,144 tokens (256K).

Where can I download test cache GGUF?

The files are on Hugging Face in the Rpo5777/test-cache 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 Rpo5777

All by Rpo5777 →

More Test models

All Test →

Other large models

All large models →