Updated minutes ago
Allen AI

Molmo 72B

Allen AI · dense · 72B parameters · 8,192 context

Quality
78.0
Calculate ROI →Compare with othersFine-Tune This Model →

Parameters

72B

Context Window

8K tokens

Architecture

Dense

Best GPU

H200 SXM

Quality Score

78/100

Intelligence Brief

Molmo 72B is a 72B parameter DENSE model from Allen AI, featuring Grouped Query Attention (GQA) with 80 layers and 8,192 hidden dimensions. With a 8,192 token context window, it supports tools, vision, structured output, code, math, multilingual, reasoning. On standardized benchmarks, it achieves MMLU 82, HumanEval 52, GSM8K 78. For self-hosted inference, H200 SXM delivers optimal throughput at $2553/month.

Architecture Details

TypeDENSE
Total Parameters72B
Active Parameters72B
Layers80
Hidden Dimension8,192
Attention Heads64
KV Heads8
Head Dimension128
Vocab Size152,064

Memory Requirements

BF16 Weights

144.0 GB

FP8 Weights

72.0 GB

INT4 Weights

36.0 GB

KV-Cache per Token589824 bytes
Activation Estimate3.00 GB

Fits on (single GPU) — most practical first

BEST FITRTX A600048GBINT4A4048GBINT4L40S48GBINT4L4048GBINT4RTX 6000 Ada48GBINT4Radeon PRO W790048GBINT4L2048GBINT4Instinct MI21064GBINT4A1664GBINT4H100 SXM80GBINT4H100 PCIe80GBINT4A100 80GB SXM80GBINT4

GPU Compatibility Matrix

Molmo 72B is compatible with 37% of GPU configurations across 41 GPUs at 3 precision levels.

BF16 (Full)
FP8 (Half)
INT4 (Quarter)
Blackwell(7 GPUs)
B200 NVL (pair)360GB
60%
80%
90%
B300288GB
50%
75%
88%
B100 SXM192GB
25%
63%
81%
GB200 NVL72 (per GPU)192GB
25%
63%
81%
Hopper(7 GPUs)
H100 NVL 94GB (per GPU pair)188GB
23%
62%
81%
H200 SXM141GB
✗
49%
74%
H2096GB
✗
25%
63%
GH20096GB
✗
25%
63%
Ada Lovelace(11 GPUs)
L40S48GB
✗
✗
25%
L4048GB
✗
✗
25%
RTX 6000 Ada48GB
✗
✗
25%
L2048GB
✗
✗
25%
Ampere(16 GPUs)
A100 80GB SXM80GB
✗
10%
55%
A100 80GB PCIe80GB
✗
10%
55%
A1664GB
✗
✗
44%
RTX A600048GB
✗
✗
25%
Legend:No fitVery tightTightModerateGoodExcellent

GPU Recommendations

H200 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

100/100

score

Throughput

557.7 tok/s

Latency (ITL)

1.8ms

Est. TTFT

0ms

Cost/Month

$2553

Cost/M Tokens

$1.74

Use this config →
B200 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

98/100

score

Throughput

560.0 tok/s

Latency (ITL)

1.8ms

Est. TTFT

0ms

Cost/Month

$4261

Cost/M Tokens

$2.90

Use this config →
B100 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

98/100

score

Throughput

560.0 tok/s

Latency (ITL)

1.8ms

Est. TTFT

0ms

Cost/Month

$4271

Cost/M Tokens

$2.90

Use this config →

Deployment Options

API

API Deployment

No API pricing available

Self-Hosted

Single GPU

H200 SXM

$2553/mo

Min VRAM: 72 GB

Scale

Multi-GPU

H100 SXM x2

560.0 tok/s

TP· $3587/mo

Open Full Calculator →

API Pricing Comparison

No API pricing data available for this model.

Performance Estimates

Throughput by GPU

H200 SXM
557.7 tok/s
B200 SXM
560.0 tok/s
B100 SXM
560.0 tok/s

VRAM Breakdown (H200 SXM, FP8)

Weights
Act
Weights 72.0 GBKV-Cache 2.7 GBActivations 24.0 GBOverhead 3.6 GB

Precision Impact

bf16

144.0 GB

weights/GPU

fp8

72.0 GB

weights/GPU

~557.7 tok/s

int4

36.0 GB

weights/GPU

Quality Benchmarks

Above Average
84th percentile across all models
MMLU
82.0
Average (63th pctile)
HumanEval
52.0
Average (52th pctile)
GSM8K
78.0
Below Average (43th pctile)
MT-Bench
82.0
Bottom 25% (0th pctile)

Capabilities

Features

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

Supported Frameworks

vllmsglang

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Molmo 72B

Similar Models

Dolphin 2.9 72B

72B params · dense

Quality: 50

Larger context, Lower qualityCompare →

Qwen 2.5 72B

72.7B params · dense

Quality: 77

from $0.90/M

Larger contextCompare →

Qwen 2.5 Math 72B

72.7B params · dense

Quality: 50

from $0.90/M

Lower qualityCompare →

Qwen 2.5 VL 72B

72.7B params · dense

Quality: 50

from $0.90/M

Larger context, Lower qualityCompare →

DeepSeek R1 Distill 70B

70.6B params · dense

Quality: 88

from $0.88/M

Larger context, Higher qualityCompare →

Frequently Asked Questions

How much VRAM does Molmo 72B need for inference?

Molmo 72B requires approximately 144.0 GB of VRAM at BF16 precision, 72.0 GB at FP8, or 36.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (589824 bytes per token) and activations (~3.00 GB).

What is the best GPU for Molmo 72B?

The top recommended GPU for Molmo 72B is the H200 SXM using FP8 precision. It achieves approximately 557.7 tokens/sec at an estimated cost of $2553/month ($1.74/M tokens). Score: 100/100.

How much does Molmo 72B inference cost?

Molmo 72B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.