DeepSeek/Dense

DeepSeekJanus-Pro 7B

Janus Pro 7B — DeepSeek's multimodal model for image understanding and generation.

chatvision
7.3B
Parameters
4K
Context length
8
Benchmarks
6
Quantizations
80K
HF downloads
Architecture
Dense
Released
2025-01-27
Layers
30
KV Heads
30
Head Dim
128
Family
deepseek

Quantization Options

QuantBitsVRAMQuality
Q4_K_M4.895.0 GBgood
Q5_K_S5.575.6 GBgood
Q5_K_M5.75.7 GBgood
Q6_K6.566.5 GBexcellent
Q8_08.58.2 GBlossless
FP161615.1 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 JANUS-PRO 7B NOW

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

Community Ratings

Loading ratings...

Benchmarks (8)

MMBench67.0
MMMU41.0
IFEval36.8
BBH27.6
MMLU-PRO22.0
MUSR12.4
GPQA9.1
MATH6.6

Run this model

Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run deepseek:7b-q4_K_M

Tag may need adjustment — check ollama.com/library/deepseek 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 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 RTX 3050 6GB
6 GB VRAM • 168 GB/s
NVIDIA
$169
Intel Arc A380
6 GB VRAM • 186 GB/s
INTEL
$129
NVIDIA RTX 2060 6GB
6 GB VRAM • 336 GB/s
NVIDIA
$150
NVIDIA GTX 1660 Ti
6 GB VRAM • 288 GB/s
NVIDIA
$140
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 Janus-Pro 7B

Build Hardware for Janus-Pro 7B

Janus Pro 7B — DeepSeek's multimodal model for image understanding and generation.

▸ SPEC SHEET

Janus-Pro 7B7.3B Dense.

▸ SPECIFICATIONS
PARAMETERS
7.3B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
4K tokens
CAPABILITIES
chat, vision
RELEASE DATE
2025-01-27
PROVIDER
DeepSeek
FAMILY
deepseek
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.895.0 GB94%
Q5_K_S5.575.6 GB96%
Q5_K_M5.75.7 GB96%
Q6_K6.566.5 GB97%
Q8_08.58.2 GB100%
FP161615.1 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO22.0
MATH6.6
IFEval36.8
BBH27.6
MMMU41.0
GPQA9.1
MUSR12.4
MMBench67.0