Updated minutes ago
DeepSeek

Janus-Pro 7B

DeepSeek · dense · 7B parameters · 8,192 context

Quality
62.0
Calculate ROI →Compare with othersFine-Tune This Model →

Parameters

7B

Context Window

8K tokens

Architecture

Dense

Best GPU

A10G

Quality Score

62/100

Intelligence Brief

Janus-Pro 7B is a 7B parameter DENSE model from DeepSeek, featuring Multi-Head Attention (MHA) with 32 layers and 4,096 hidden dimensions. With a 8,192 token context window, it supports vision, code. On standardized benchmarks, it achieves MMLU 68, HumanEval 38, GSM8K 65. For self-hosted inference, A10G delivers optimal throughput at $285/month.

Architecture Details

TypeDENSE
Total Parameters7B
Active Parameters7B
Layers32
Hidden Dimension4,096
Attention Heads32
KV Heads32
Head Dimension128
Vocab Size100,000

Memory Requirements

BF16 Weights

14.0 GB

FP8 Weights

7.0 GB

INT4 Weights

3.5 GB

KV-Cache per Token262144 bytes
Activation Estimate0.80 GB

Fits on (single GPU) — most practical first

BEST FITRTX 40608GBINT4RTX 30708GBINT4RTX 308010GBFP8RTX 4070 Ti12GBFP8RTX 4070 Super12GBFP8RTX 306012GBFP8A400016GBFP8RTX 408016GBFP8T416GBFP8V100 16GB16GBFP8RTX 4060 Ti 16GB16GBFP8A216GBFP8

GPU Compatibility Matrix

Janus-Pro 7B is compatible with 95% of GPU configurations across 41 GPUs at 3 precision levels.

BF16 (Full)
FP8 (Half)
INT4 (Quarter)
Blackwell(7 GPUs)
B200 NVL (pair)360GB
96%
98%
99%
B300288GB
95%
98%
99%
B100 SXM192GB
93%
96%
98%
GB200 NVL72 (per GPU)192GB
93%
96%
98%
Hopper(7 GPUs)
H100 NVL 94GB (per GPU pair)188GB
93%
96%
98%
H200 SXM141GB
90%
95%
98%
H2096GB
85%
93%
96%
GH20096GB
85%
93%
96%
Ada Lovelace(11 GPUs)
L40S48GB
71%
85%
93%
L4048GB
71%
85%
93%
RTX 6000 Ada48GB
71%
85%
93%
L2048GB
71%
85%
93%
Ampere(16 GPUs)
A100 80GB SXM80GB
83%
91%
96%
A100 80GB PCIe80GB
83%
91%
96%
A1664GB
78%
89%
95%
RTX A600048GB
71%
85%
93%
Legend:No fitVery tightTightModerateGoodExcellent

GPU Recommendations

A10Goptimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

231.4 tok/s

Latency (ITL)

4.3ms

Est. TTFT

1ms

Cost/Month

$285

Cost/M Tokens

$0.47

Use this config →
A30optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

359.9 tok/s

Latency (ITL)

2.8ms

Est. TTFT

0ms

Cost/Month

$332

Cost/M Tokens

$0.35

Use this config →
RTX 4090optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

388.8 tok/s

Latency (ITL)

2.6ms

Est. TTFT

0ms

Cost/Month

$370

Cost/M Tokens

$0.36

Use this config →

Deployment Options

API

API Deployment

No API pricing available

Self-Hosted

Single GPU

A10G

$285/mo

Min VRAM: 7 GB

Scale

Multi-GPU

RTX 3080 x2

452.6 tok/s

TP· $266/mo

Open Full Calculator →

API Pricing Comparison

No API pricing data available for this model.

Performance Estimates

Throughput by GPU

A10G
231.4 tok/s
A30
359.9 tok/s
RTX 4090
388.8 tok/s

VRAM Breakdown (A10G, BF16)

Weights
KV
Act
Weights 14.0 GBKV-Cache 8.6 GBActivations 6.4 GBOverhead 1.1 GB

Precision Impact

bf16

14.0 GB

weights/GPU

~231.4 tok/s

fp8

7.0 GB

weights/GPU

int4

3.5 GB

weights/GPU

Quality Benchmarks

Average
65th percentile across all models
MMLU
68.0
Below Average (27th pctile)
HumanEval
38.0
Bottom 25% (24th pctile)
GSM8K
65.0
Below Average (27th pctile)

Capabilities

Features

✗ Tool Use✓ Vision✓ Code✗ Math✗ Reasoning✗ Multilingual✗ Structured Output

Supported Frameworks

vllmollama

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Janus-Pro 7B

Similar Models

OLMo 2 7B

7B params · dense

Quality: 50

Lower qualityCompare →

Command R 7B

7B params · dense

Quality: 68

from $0.15/M

Larger context, Higher qualityCompare →

Falcon 7B

7B params · dense

Quality: 37

from $0.15/M

Smaller context, Lower qualityCompare →

Zephyr 7B

7B params · dense

Quality: 50

Larger context, Lower qualityCompare →

Vicuna 7B

7B params · dense

Quality: 50

Lower qualityCompare →

Frequently Asked Questions

How much VRAM does Janus-Pro 7B need for inference?

Janus-Pro 7B requires approximately 14.0 GB of VRAM at BF16 precision, 7.0 GB at FP8, or 3.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (262144 bytes per token) and activations (~0.80 GB).

What is the best GPU for Janus-Pro 7B?

The top recommended GPU for Janus-Pro 7B is the A10G using BF16 precision. It achieves approximately 231.4 tokens/sec at an estimated cost of $285/month ($0.47/M tokens). Score: 100/100.

How much does Janus-Pro 7B inference cost?

Janus-Pro 7B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.