Zyphra/Dense

ZZamba2 2.7B

Zamba2-2.7B-Instruct is obtained from Zamba2-2.7B by fine-tuning on instruction-following and chat datasets. Specifically:

chat
2.7B
Parameters
4K
Context length
1
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2024-10-15
Layers
54
KV Heads
32
Head Dim
80
Family
other

Quantization Options

QuantBitsVRAMQuality
Q4_K_M4.892.1 GBgood
Q5_K_S5.572.4 GBgood
Q5_K_M5.72.4 GBgood
Q6_K6.562.7 GBexcellent
Q8_08.53.4 GBlossless
FP16165.9 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 ZAMBA2 2.7B NOW

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

Community Ratings

Loading ratings...

Benchmarks (1)

IFEval48.0

Run this model

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

Tag may need adjustment — check ollama.com/library/other 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 Zamba2 2.7B

Build Hardware for Zamba2 2.7B
▸ SPEC SHEET

Zamba2 2.7B2.7B Dense.

▸ SPECIFICATIONS
PARAMETERS
2.7B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
4K tokens
CAPABILITIES
chat
RELEASE DATE
2024-10-15
PROVIDER
Zyphra
FAMILY
other
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.892.1 GB94%
Q5_K_S5.572.4 GB96%
Q5_K_M5.72.4 GB96%
Q6_K6.562.7 GB97%
Q8_08.53.4 GB100%
FP16165.9 GB100%
§ 01BENCHMARK SCORES
IFEval48.0