FitMyLLM
HuggingFace/Dense

HuggingFaceZephyr 3B

Zephyr 3B — HuggingFace's DPO-tuned small model for helpful conversation.

chat
2.79B
Parameters
4K
Context length
6
Benchmarks
6
Quantizations
50K
HF downloads
Architecture
Dense
Released
2024-01-17
Layers
2
KV Heads
4
Head Dim
4
Family
zephyr

Quantization Options

QuantBitsVRAM @ 4KQuality
Q4_K_M4.89
2.2 GB
good
Q5_K_S5.57
2.4 GB
good
Q5_K_M5.7
2.5 GB
good
Q6_K6.56
2.8 GB
excellent
Q8_08.5
3.5 GB
lossless
FP1616
6.1 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 Zephyr 3B now

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

Community Ratings

Loading ratings...

Benchmarks (6)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run hf.co/bartowski/stablelm-zephyr-3b-GGUF:Q4_K_M

Not in Ollama's library: Ollama pulls the GGUF from Hugging Face (bartowski/stablelm-zephyr-3b-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 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 Zephyr 3B

Build Hardware for Zephyr 3B

Zephyr 3B — HuggingFace's DPO-tuned small model for helpful conversation.

Spec sheet

Zephyr 3B — 2.79B Dense.

Specifications
Parameters
2.79B
Architecture
Dense Transformer
Context Length
4K tokens
Capabilities
chat
Release Date
2024-01-17
Provider
HuggingFace
Family
zephyr
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%
Benchmark scores
MMLU-PRO8.5
MATH4.3
IFEval49.0
BBH14.8
GPQA0.0
MUSR9.8
Compatible GPUs
30 @ Q4_K_M