SA

sandepa ai coder small moe 235m

SandepaGGUF by sandepaAIUpdated 2026-07-23
Download on Hugging Face
Parameters219M
Context512
Layers12
Architecturellama
Smallest quant0.4 GB
Quick answer

sandepa ai coder small moe 235m needs about 1.2 GB of memory at its main file (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU.

sandepa ai coder small moe 235m is a 219M-parameter Sandepa model in GGUF format, quantized by sandepaAI. Its trained context length is 512 tokens. The repository has 1 quant file, from 0.4 GB to 0.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.4 GB 1.0 GB
Fits Get file →

What GPU do you need for sandepa ai coder small moe 235m?

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 the main file (0.4 GB file, about 1.2 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters219M (approximate, mixture of experts)
Layers12
Trained context512 tokens
KV cache (fp16)36 KB per token

Source

Quantized bysandepaAI
FamilySandepa
Downloads (HF)32
Last updated2026-07-23

Frequently asked questions about sandepa ai coder small moe 235m

How much VRAM does sandepa ai coder small moe 235m need?

About 1.2 GB at its main file with an 8K context window. That is the 0.4 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 sandepa ai coder small moe 235m on an 8 GB GPU?

Yes, with the smaller files: the 0.4 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of sandepa ai coder small moe 235m GGUF?

It depends on the quant: file is 0.4 GB.

What context length does sandepa ai coder small moe 235m support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 512.

Where can I download sandepa ai coder small moe 235m GGUF?

The files are on Hugging Face in the sandepaAI/sandepa_ai_coder_small_moe_235m 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 sandepaAI

All by sandepaAI →

More Sandepa models

All Sandepa →

Other tiny models

All tiny models →