Databricks/Dense

DDolly v2 3B

Databricks' instruction-tuned model. One of the first open instruction models.

chat
2.8B
Parameters
2K
Context length
6
Benchmarks
6
Quantizations
100K
HF downloads
Architecture
Dense
Released
2023-04-12
Layers
32
KV Heads
16
Head Dim
80
Family
dolly

Quantization Options

QuantBitsVRAMQuality
Q4_K_M4.892.2 GBgood
Q5_K_S5.572.4 GBgood
Q5_K_M5.72.5 GBgood
Q6_K6.562.8 GBexcellent
Q8_08.53.5 GBlossless
FP16166.1 GBlossless

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 DOLLY V2 3B NOW

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

Community Ratings

Loading ratings...

Benchmarks (6)

IFEval22.5
BBH3.3
MUSR3.2
MMLU-PRO1.6
MATH1.5
GPQA1.5

Run this model

Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run dolly:3b-q4_K_M

Tag may need adjustment — check ollama.com/library/dolly for available tags.

▸ 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 C2050
3 GB VRAM • 144 GB/s
NVIDIA
NVIDIA Tesla M2050
3 GB VRAM • 148 GB/s
NVIDIA
NVIDIA Tesla S2050
3 GB VRAM • 148 GB/s
NVIDIA

Find the best GPU for Dolly v2 3B

Build Hardware for Dolly v2 3B

Databricks' instruction-tuned model. One of the first open instruction models.

▸ SPEC SHEET

Dolly v2 3B2.8B Dense.

▸ SPECIFICATIONS
PARAMETERS
2.8B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
2K tokens
CAPABILITIES
chat
RELEASE DATE
2023-04-12
PROVIDER
Databricks
FAMILY
dolly
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.892.2 GB94%
Q5_K_S5.572.4 GB96%
Q5_K_M5.72.5 GB96%
Q6_K6.562.8 GB97%
Q8_08.53.5 GB100%
FP16166.1 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO1.6
MATH1.5
IFEval22.5
BBH3.3
GPQA1.5
MUSR3.2