CA

Caliber 4b

CaliberGGUF by svebbroUpdated 2026-06-15
Download on Hugging Face
Parameters4.33B
Context256K
Layers33
Architectureqwen35
Smallest quant2.3 GB
Quick answer

Caliber 4b needs about 3.9 GB of memory at Q3_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Caliber 4b is a 4.33B-parameter Caliber model in GGUF format, quantized by svebbro. Its trained context length is 256K tokens. The repository has 1 quant file, from 2.3 GB (Q3_K_M) to 2.3 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M2.3 GB 3.9 GB
Fits Get file →

What GPU do you need for Caliber 4b?

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: the best quant that fits is Q3_K_M (2.3 GB file, about 3.9 GB in use).

Which Caliber 4b quant should you choose?

Q3_K_M (2.3 GB) is the middle option in this repository. 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

Architectureqwen35
Parameters4.33B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized bysvebbro
FamilyCaliber
Downloads (HF)5
Last updated2026-06-15

Frequently asked questions about Caliber 4b

How much VRAM does Caliber 4b need?

About 3.9 GB at Q3_K_M with an 8K context window. That is the 2.3 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 Caliber 4b on an 8 GB GPU?

Yes, with Q3_K_M: the 2.3 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Caliber 4b GGUF?

It depends on the quant: Q3_K_M is 2.3 GB.

What context length does Caliber 4b support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download Caliber 4b GGUF?

The files are on Hugging Face in the svebbro/Caliber-4b 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 →

Other small models

All small models →