CA

Castor E4B v1b

CastorGGUF by BeaverAIUpdated 2026-10-26
Download on Hugging Face
Parameters7.52B
Context128K
Layers42
Architecturegemma4
Smallest quant4.9 GB
Quick answer

Castor E4B v1b needs about 7.3 GB of memory at Q4_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 4.9 GB (Q3_K_M) to 8.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Castor E4B v1b – 7.52B Gemma4 model for reasoning and tool use

Castor E4B v1b is a 7.52B parameter Gemma4 model. It supports reasoning and tool usage. The model was trained on 131072 context tokens.

Good at

  • Reasoning
  • Tool integration
  • Large context handling

Limits

  • No vision support
  • License not specified
  • No mixture of experts

Best for

  • Chatbot development
  • Code assistance
  • Data analysis queries

Who it’s for. Developers building conversational AI that requires reasoning and tool use. Suitable for applications needing a large context window and moderate parameter size.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M4.9 GB 6.8 GB
Fits Get file →
Q4_K_M5.4 GB 7.3 GB
Tight Get file →
Q5_K_M5.8 GB 7.7 GB
Tight Get file →
Q6_K6.3 GB 8.2 GB
Too big Get file →
Q8_08.1 GB 10.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.39 GB file, ~7.3 GB memory). For 12 GB VRAM, Q5_K_M (5.82 GB file, ~7.7 GB memory). For 16 GB VRAM, Q6_K (6.27 GB file, ~8.2 GB memory).

What GPU do you need for Castor E4B v1b?

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 Q5_K_M (5.8 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 10.0 GB in use).

Which Castor E4B v1b quant should you choose?

Q4_K_M is the usual starting point for Castor E4B v1b: it balances file size and quality well. Here it is a 5.4 GB file.

The Q8_0 file is 8.1 GB, about 1.5 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 Q3_K_M at 4.9 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

Architecturegemma4
Parameters7.52B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized byBeaverAI
FamilyCastor
Downloads (HF)1,129
Last updated2026-10-26

Frequently asked questions about Castor E4B v1b

How much VRAM does Castor E4B v1b need?

About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.4 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 Castor E4B v1b on an 8 GB GPU?

Yes, with Q5_K_M: the 5.8 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Castor E4B v1b GGUF?

It depends on the quant: Q3_K_M is 4.9 GB, Q4_K_M is 5.4 GB, Q5_K_M is 5.8 GB, Q6_K is 6.3 GB, Q8_0 is 8.1 GB.

What context length does Castor E4B v1b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Castor E4B v1b GGUF?

The files are on Hugging Face in the BeaverAI/Castor-E4B-v1b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Castor E4B v1b on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires about 7.3 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What context length can it handle?

It was trained on 131072 tokens and can handle up to that context length.

Similar models

Browse all →

More from BeaverAI

All by BeaverAI →

More Castor models

All Castor →

Other small models

All small models →