How much VRAM does bitnet_b1_58-large need?

TQ2_0 is exactly 217,082,208 bytes (0.20 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is bitnet_b1_58-large's KV cache?

4.50 GiB at 32K context with an f16 cache, computed per layer from the model's architecture. Quantizing the cache to q8_0 roughly halves it.

1bitLLM · text

bitnet_b1_58-large

1bitLLM/bitnet_b1_58-large

bitnet_b1_58-large at TQ2_0 is exactly 217,082,208 bytes (0.20 GiB / 0.22 GB) — an effective 2.383 bits per weight, not the nominal 2. Its KV cache at 32K is 4.50 GiB.

From the file· summed from 1 file(s)From the file· KV per layer

Parameters

729M

Architecture

bitnet

24 layers

Context

2,048

native (config.json)

License

mit

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
TQ2_0	0.20 GiB	217,082,208	2.383	—	gianni-cor

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.56 GiB	0.56 GiB	—	24 / 0 / 0
8,192	1.13 GiB	1.13 GiB	—	24 / 0 / 0
16,384	2.25 GiB	2.25 GiB	—	24 / 0 / 0
32,768	4.50 GiB	4.50 GiB	—	24 / 0 / 0
65,536	9.00 GiB	9.00 GiB	—	24 / 0 / 0
131,072	18.00 GiB	18.00 GiB	—	24 / 0 / 0

Compare with

same modality, comparable size

vs Llama-3.2-1B-Instruct vs ced-base vs Qwen3-1.7B vs embeddinggemma-300m vs Qwen3-0.6B vs LFM2.5-1.2B-Instruct 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 0.38 GiB. The real file is 0.20 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json

Layers

Attention heads

KV heads

Head dim

Hidden size

1536

Vocab

32,002

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does bitnet_b1_58-large need?: TQ2_0 is exactly 217,082,208 bytes (0.20 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is bitnet_b1_58-large's KV cache?: 4.50 GiB at 32K context with an f16 cache, computed per layer. Quantizing the cache to q8_0 roughly halves it, which is often the difference between a context length fitting and not.
Which quantization of bitnet_b1_58-large 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.