How much VRAM does Qwopus3.6-27B-Coder-MTP need?

NVFP4 is exactly 15,715,852,640 bytes (14.64 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

Jackrong · text

Qwopus3.6-27B-Coder-MTP

Jackrong/Qwopus3.6-27B-Coder-MTP

Qwopus3.6-27B-Coder-MTP at NVFP4 is exactly 15,715,852,640 bytes (14.64 GiB / 15.72 GB)

From the file· summed from 1 file(s)

Parameters

—

Architecture

clip

Context

—

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
NVFP4	14.64 GiB	15,715,852,640	—	—	s-batman

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs Qwen3.6-27B vs Qwen3.8-27B vs gemma-4-12B-it-qat-q4_0-unquantized vs gemma-4-E4B-it vs Qwen3-30B-A3B-Thinking-2507 All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts NVFP4 at roughly 0.00 GiB. The real file is 14.64 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

Architecture unavailable — this repository is gated and no ungated mirror was found. Exact file sizes above are still authoritative; only the KV math needs the config.

Questions people ask

How much VRAM does Qwopus3.6-27B-Coder-MTP need?: NVFP4 is exactly 15,715,852,640 bytes (14.64 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of Qwopus3.6-27B-Coder-MTP should I use?: Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.