Skip to content
Updated minutes ago
LMSYS

Vicuna 33B

LMSYS · dense · 33B parameters · 2,048 context

Quality
50.0

Parameters

33B

Context Window

2K tokens

Architecture

Dense

Best GPU

H20

Intelligence Brief

Vicuna 33B is a 33B parameter DENSE model from LMSYS, featuring Multi-Head Attention (MHA) with 60 layers and 6,656 hidden dimensions. With a 2,048 token context window, it supports code. For self-hosted inference, H20 delivers optimal throughput at $940/month.

Architecture Details

TypeDENSE
Total Parameters33B
Active Parameters33B
Layers60
Hidden Dimension6,656
Attention Heads52
KV Heads52
Head Dimension128
Vocab Size32,000

Memory Requirements

BF16 Weights

66.0 GB

FP8 Weights

33.0 GB

INT4 Weights

16.5 GB

KV-Cache per Token1597440 bytes
Activation Estimate2.00 GB

GPU Compatibility Matrix

Vicuna 33B is compatible with 57% 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

H20optimal

FP8 · 1 GPU · tensorrt-llm

100/100

score

Throughput

1.0K tok/s

Latency (ITL)

1.0ms

Est. TTFT

0ms

Cost/Month

$940

Cost/M Tokens

$0.35

Use this config →
H200 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

95/100

score

Throughput

1.1K tok/s

Latency (ITL)

1.0ms

Est. TTFT

0ms

Cost/Month

$2553

Cost/M Tokens

$0.93

Use this config →
H100 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

95/100

score

Throughput

849.3 tok/s

Latency (ITL)

1.2ms

Est. TTFT

0ms

Cost/Month

$1794

Cost/M Tokens

$0.80

Use this config →

Deployment Options

API

API Deployment

No API pricing available

Self-Hosted

Single GPU

H20

$940/mo

Min VRAM: 33 GB

Scale

Multi-GPU

RTX A6000 x2

110.6 tok/s

TP· $930/mo

API Pricing Comparison

No API pricing data available for this model.

Performance Estimates

Throughput by GPU

H20
1.0K tok/s
H200 SXM
1.1K tok/s
H100 SXM
849.3 tok/s

VRAM Breakdown (H20, FP8)

Weights
KV
Act
Weights 33.0 GBKV-Cache 13.1 GBActivations 16.0 GBOverhead 1.7 GB

Precision Impact

bf16

66.0 GB

weights/GPU

fp8

33.0 GB

weights/GPU

~1.0K tok/s

int4

16.5 GB

weights/GPU

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgiollama

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Vicuna 33B

Similar Models

Larger context, Smaller modelCompare →
Larger contextCompare →

Grok-3 Mini

33B params · dense

Quality: 78

from $0.50/M

Larger context, Higher qualityCompare →
Larger context, Higher qualityCompare →

Frequently Asked Questions

How much VRAM does Vicuna 33B need for inference?

Vicuna 33B requires approximately 66.0 GB of VRAM at BF16 precision, 33.0 GB at FP8, or 16.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (1597440 bytes per token) and activations (~2.00 GB).

What is the best GPU for Vicuna 33B?

The top recommended GPU for Vicuna 33B is the H20 using FP8 precision. It achieves approximately 1.0K tokens/sec at an estimated cost of $940/month ($0.35/M tokens). Score: 100/100.

How much does Vicuna 33B inference cost?

Vicuna 33B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.