Skip to content
Updated minutes ago
TII

Falcon 180B

TII · dense · 180B parameters · 2,048 context

Quality
60.0

Parameters

180B

Context Window

2K tokens

Architecture

Dense

Best GPU

B200 SXM

Cheapest API

$2.40/M

Quality Score

60/100

Intelligence Brief

Falcon 180B is a 180B parameter DENSE model from TII, featuring Grouped Query Attention (GQA) with 80 layers and 14,848 hidden dimensions. With a 2,048 token context window, it supports code, multilingual. On standardized benchmarks, it achieves MMLU 68.6, HumanEval 33, GSM8K 55. The most cost-effective API deployment is via tii at $2.40/M output tokens. For self-hosted inference, B200 SXM delivers optimal throughput at $8522/month.

Architecture Details

TypeDENSE
Total Parameters180B
Active Parameters180B
Layers80
Hidden Dimension14,848
Attention Heads232
KV Heads8
Head Dimension64
Vocab Size65,024

Memory Requirements

BF16 Weights

360.0 GB

FP8 Weights

180.0 GB

INT4 Weights

90.0 GB

KV-Cache per Token163840 bytes
Activation Estimate4.00 GB

GPU Compatibility Matrix

Falcon 180B is compatible with 14% of GPU configurations across 41 GPUs at 3 precision levels.

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

GPU Recommendations

B200 SXMoptimal

FP8 · 2 GPUs · tensorrt-llm

98/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$8522

Cost/M Tokens

$11.58

Use this config →
B100 SXMoptimal

FP8 · 2 GPUs · tensorrt-llm

98/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$8541

Cost/M Tokens

$11.61

Use this config →
H200 SXMoptimal

FP8 · 2 GPUs · tensorrt-llm

95/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$5106

Cost/M Tokens

$6.94

Use this config →

Deployment Options

API

API Deployment

tii

$2.40/M

output tokens

Self-Hosted

Single GPU

B200 NVL (pair)

$9965/mo

Min VRAM: 180 GB

Scale

Multi-GPU

B200 SXM x2

280.0 tok/s

TP· $8522/mo

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
tii$2.40$2.40
Cheapest

Cost Analysis

ProviderInput $/MOutput $/M~Monthly Cost
tiiBest Value$2.40$2.40$24

Cost per 1,000 Requests

Short (500 tok)

$1.68

via tii

Medium (2K tok)

$6.72

via tii

Long (8K tok)

$24.00

via tii

Performance Estimates

Throughput by GPU

B200 SXM
280.0 tok/s
B100 SXM
280.0 tok/s
H200 SXM
280.0 tok/s

VRAM Breakdown (B200 SXM, FP8)

Weights
Act
Weights 90.0 GBKV-Cache 1.3 GBActivations 32.0 GBOverhead 4.5 GB

Precision Impact

bf16

180.0 GB

weights/GPU

fp8

90.0 GB

weights/GPU

~280.0 tok/s

int4

45.0 GB

weights/GPU

Quality Benchmarks

Average
63th percentile across all models
MMLU
68.6
Below Average (29th pctile)
HumanEval
33.0
Bottom 25% (16th pctile)
GSM8K
55.0
Bottom 25% (19th pctile)
MT-Bench
72.0
Bottom 25% (0th pctile)

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgitensorrt-llm

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Falcon 180B

Similar Models

Gemini 1.5 Pro

175B params · moe

Quality: 80

from $5.00/M

Larger context, Higher quality, More expensiveCompare →

Claude 3 Opus

175B params · dense

Quality: 80

from $75.00/M

Larger context, Higher quality, More expensiveCompare →

Claude Opus 4

200B params · dense

Quality: 90

from $75.00/M

Larger context, Higher quality, More expensiveCompare →

GPT-4o

200B params · moe

Quality: 85

from $10.00/M

Larger context, Higher quality, More expensiveCompare →

GPT-4 Turbo

200B params · moe

Quality: 80

from $30.00/M

Larger context, Higher quality, More expensiveCompare →

Frequently Asked Questions

How much VRAM does Falcon 180B need for inference?

Falcon 180B requires approximately 360.0 GB of VRAM at BF16 precision, 180.0 GB at FP8, or 90.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (163840 bytes per token) and activations (~4.00 GB).

What is the best GPU for Falcon 180B?

The top recommended GPU for Falcon 180B is the B200 SXM (x2) using FP8 precision. It achieves approximately 280.0 tokens/sec at an estimated cost of $8522/month ($11.58/M tokens). Score: 98/100.

How much does Falcon 180B inference cost?

Falcon 180B API inference starts from $2.40/M input tokens and $2.40/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.