FitMyLLM
BigScience/Dense

BBLOOMZ 7B

BigScience's multilingual model trained on 46 languages. Community-built.

chatmultilingual
7.1B
Parameters
2K
Context length
7
Benchmarks
6
Quantizations
200K
HF downloads
Architecture
Dense
Released
2022-11-03
Layers
30
KV Heads
32
Head Dim
128
Family
bloom

Quantization Options

QuantBitsVRAM @ 2KQuality
Q4_K_M4.89
4.8 GB
good
Q5_K_S5.57
5.4 GB
good
Q5_K_M5.7
5.5 GB
good
Q6_K6.56
6.3 GB
excellent
Q8_08.5
8.0 GB
lossless
FP1616
14.7 GB
lossless

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

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run BLOOMZ 7B now

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

Community Ratings

Loading ratings...

Benchmarks (7)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run hf.co/TheBloke/bloomz-7b1-GGUF:Q4_K_M

Not in Ollama's library: Ollama pulls the GGUF from Hugging Face (TheBloke/bloomz-7b1-GGUF). If Q4_K_M is not in that repo, pick a file listed there.

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

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla K20c
5 GB VRAM • 208 GB/s
NVIDIA
NVIDIA Tesla K20m
5 GB VRAM • 208 GB/s
NVIDIA
NVIDIA Tesla K20s
5 GB VRAM • 208 GB/s
NVIDIA
NVIDIA Tesla C2070
6 GB VRAM • 143 GB/s
NVIDIA
NVIDIA Tesla C2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla C2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla M2070
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2070-Q
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2070
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla K20X
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA Tesla K20Xm
6 GB VRAM • 250 GB/s
NVIDIA

Find the best GPU for BLOOMZ 7B

Build Hardware for BLOOMZ 7B

BigScience's multilingual model trained on 46 languages. Community-built.

Spec sheet

BLOOMZ 7B — 7.1B Dense.

Specifications
Parameters
7.1B
Architecture
Dense Transformer
Context Length
2K tokens
Capabilities
chat, multilingual
Release Date
2022-11-03
Provider
BigScience
Family
bloom
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.894.8 GB94%
Q5_K_S5.575.4 GB96%
Q5_K_M5.75.5 GB96%
Q6_K6.566.3 GB97%
Q8_08.58.0 GB100%
FP161614.7 GB100%
Benchmark scores
HumanEval15.5
MMLU-PRO1.2
MATH0.5
IFEval13.2
BBH4.0
GPQA1.9
MUSR1.9
Compatible GPUs
30 @ Q4_K_M