How much VRAM does Ternary-Bonsai-8B need?

TQ2_0 is exactly 2,414,272,288 bytes (2.25 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

prism-ml · text

Ternary-Bonsai-8B

prism-ml/Ternary-Bonsai-8B

Ternary-Bonsai-8B at TQ2_0 is exactly 2,414,272,288 bytes (2.25 GiB / 2.41 GB) — an effective 2.359 bits per weight, not the nominal 2.

From the file· summed from 1 file(s)

Parameters

8.2B

Architecture

qwen3

Context

—

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
TQ2_0	2.25 GiB	2,414,272,288	2.359	—	vinpix

Compare with

same modality, comparable size

vs gemma-4-E4B-it vs Qwen3-4B vs Qwen3-8B vs HyperCLOVAX-SEED-Text-Instruct-1.5B vs Llama-3.2-1B-Instruct vs llama-3-youko-8b All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts TQ2_0 at roughly 4.29 GiB. The real file is 2.25 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 Ternary-Bonsai-8B need?: TQ2_0 is exactly 2,414,272,288 bytes (2.25 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of Ternary-Bonsai-8B 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.