TE

Test 22B

TestGGUF by RichardErkhovUpdated 2024-09-14
Download on Hugging Face
Parameters21.8B
Context2K
Layers40
Architecturellama
Smallest quant8.1 GB
Quick answer

Test 22B needs about 22.4 GB of memory at Q4_K_M (a 13.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 8.1 GB (Q2_K) to 23.2 GB (Q8_0).

Test 22B is a 21.8B-parameter Test model in GGUF format, quantized by RichardErkhov. Its trained context length is 2K tokens. The repository has 22 quant files, from 8.1 GB (Q2_K) to 23.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.1 GB 10.8 GB
Too big Get file →
IQ3_XS9.0 GB 11.6 GB
Too big Get file →
IQ3_S9.5 GB 12.1 GB
Too big Get file →
Q3_K_S9.5 GB 12.1 GB
Too big Get file →
IQ3_M10.0 GB 12.7 GB
Too big Get file →
Q3_K10.6 GB 13.3 GB
Too big Get file →
Q3_K_M10.6 GB 13.3 GB
Too big Get file →
Q3_K_L11.6 GB 14.3 GB
Too big Get file →
IQ4_XS11.8 GB 14.4 GB
Too big Get file →
Q4_012.3 GB 15.0 GB
Too big Get file →
IQ4_NL12.4 GB 15.1 GB
Too big Get file →
Q4_K_S12.4 GB 15.1 GB
Too big Get file →
Q4_K13.2 GB 15.9 GB
Too big Get file →
Q4_K_M13.2 GB 15.9 GB
Too big Get file →
Q4_113.7 GB 16.4 GB
Too big Get file →
Q5_015.0 GB 17.7 GB
Too big Get file →
Q5_K_S15.0 GB 17.7 GB
Too big Get file →
Q5_K15.5 GB 18.2 GB
Too big Get file →
Q5_K_M15.5 GB 18.2 GB
Too big Get file →
Q5_116.4 GB 19.1 GB
Too big Get file →
Q6_K17.9 GB 20.6 GB
Too big Get file →
Q8_023.2 GB 25.9 GB
Too big Get file →

What GPU do you need for Test 22B?

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_1 (13.7 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (17.9 GB file, about 27.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (23.2 GB file, about 32.4 GB in use).

Which Test 22B quant should you choose?

Q4_K_M is the usual starting point for Test 22B: it balances file size and quality well. Here it is a 13.2 GB file.

The Q8_0 file is 23.2 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 8.1 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
Parameters21.8B
Layers40
Trained context2,048 tokens
KV cache (fp16)1040 KB per token

Source

Quantized byRichardErkhov
FamilyTest
Downloads (HF)203
Last updated2024-09-14

Frequently asked questions about Test 22B

How much VRAM does Test 22B need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 13.2 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 22B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Test 22B GGUF?

It depends on the quant: Q2_K is 8.1 GB, IQ3_XS is 9.0 GB, IQ3_S is 9.5 GB, Q3_K_S is 9.5 GB, IQ3_M is 10.0 GB, Q3_K is 10.6 GB and 16 more.

What context length does Test 22B support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 8.7 GB at 8K and 2.2 GB at 2K.

Where can I download Test 22B GGUF?

The files are on Hugging Face in the RichardErkhov/Devio_-_test-22B-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 RichardErkhov

All by RichardErkhov →

More Test models

All Test →

Other medium models

All medium models →