BigScience/Dense

Bbloom 176.2B

Name: bloom 176.2B
Author: BigScience

chat

176.2B

Parameters

Context length

Benchmarks

Quantizations

HF downloads

Architecture

Dense

Released

2022-07-06

Layers

KV Heads

112

Head Dim

128

Family

bloom

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	52.9 GB	low
IQ2_M	2.93	65.0 GB	low
Q2_K	3.16	70.1 GB	low
IQ3_XXS	3.25	72.1 GB	low
IQ3_XS	3.5	77.6 GB	low
Q3_K_S	3.64	80.7 GB	low
IQ3_M	3.76	83.3 GB	low
Q3_K_M	4	88.6 GB	low
Q3_K_L	4.3	95.2 GB	moderate
IQ4_XS	4.46	98.7 GB	moderate
Q4_K_S	4.67	103.3 GB	moderate
Q4_K_M	4.89	108.2 GB	good
Q5_K_S	5.57	123.2 GB	good
Q5_K_M	5.7	126.0 GB	good
Q6_K	6.56	145.0 GB	excellent
Q8_0	8.5	187.7 GB	lossless
FP16	16	352.9 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN BLOOM 176.2B NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (1)

HumanEval15.0

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run bloom:176b-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace Ollama Library GGUF Downloads Build Hardware