BitNet b1.58 3B — VRAM, Speed & Local Setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

作者： Jakub Rusinowski · 最后更新： 2024年3月1日

Model library → BitNet b1.58 → BitNet b1.58 3B

A 3B parameter model that outperforms Llama 3B while using a fraction of the energy. Optimized for CPU inference via bitnet.cpp.

BitNet b1.58 3B needs about 3 GB of VRAM at 1.58-bit — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters	3 Billion
Context window	2,048
Architecture	BitNet (Ternary)
Provider	Microsoft
Licence	MIT
Specified at	1.58-bit
System RAM	4 GB
Record updated	2024-03-01

Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.

Licence

MIT — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB). Weights plus framework overhead only — this model publishes no architecture we can read, so no KV cache is included. A real session needs more; the figure is a floor, not a target. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

Quant	Bits/weight	Weights	VRAM needed	Est. speed	Fit on 24 GB
Q2_K	2.63	1.1 GB	1.9 GB	~234 tok/s (est.)	Fits comfortably
Q3_K_M	3.41	1.4 GB	2.2 GB	~213 tok/s (est.)	Fits comfortably
Q4_K_M	4.83	2 GB	2.8 GB	~183 tok/s (est.)	Fits comfortably
Q5_K_M	5.67	2.4 GB	3.2 GB	~168 tok/s (est.)	Fits comfortably
Q6_K	6.56	2.7 GB	3.5 GB	~156 tok/s (est.)	Fits comfortably
Q8_0	8.50	3.5 GB	4.3 GB	~134 tok/s (est.)	Fits comfortably
F16	16.00	6.6 GB	7.4 GB	~86 tok/s (est.)	Fits comfortably

Want to set your own context length and KV-cache quantization? Use the interactive VRAM calculator.

购买此硬件 Intel Arc B570 10GB — 10 GB VRAM · 150 W board power 立即云端部署 RunPod 上的 RTX 4090 — 低至 $0.34/小时 · 价格核实于 2026-07

或在 Vast.ai 比较，低至 $0.35/小时 (typical low · varies)

作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。

Recommended GPU

The cheapest catalogued GPU that runs BitNet b1.58 3B is the Intel Arc B570 (10 GB).

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。

Intel Arc B570 10GB

10 GB VRAM · 150 W board power

2026年价格波动较大——请以当前商品页价格为准。

在亚马逊查看价格

How to Run BitNet b1.58 3B

Install Ollama, then run:

ollama run hf.co/1bitLLM/bitnet_b1_58-3B

Weights on Hugging Face: 1bitLLM/bitnet_b1_58-3B.

Best for: research, edge devices, cpu inference.

Can I Run BitNet b1.58 3B on My GPU?

BitNet b1.58 3B — Frequently Asked Questions

How much VRAM does BitNet b1.58 3B need?

About 3 GB at 1.58-bit — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does BitNet b1.58 3B run on an RTX 4090 (24 GB)?

Yes. BitNet b1.58 3B needs about 3 GB at 1.58-bit, inside a 24 GB card, at an estimated 183 tokens/sec.

How do I run BitNet b1.58 3B locally?

Install Ollama and run `ollama run hf.co/1bitLLM/bitnet_b1_58-3B`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

← All BitNet b1.58 models | VRAM calculator | Check your own hardware