SeamlessM4T v2 Large
Meta · dense · 2.3B parameters · 4,096 context
Parameters
2.3B
Context Window
4K tokens
Architecture
Dense
Best GPU
RTX 4060
Intelligence Brief
SeamlessM4T v2 Large is a 2.3B parameter DENSE model from Meta, featuring Multi-Head Attention (MHA) with 24 layers and 1,024 hidden dimensions. With a 4,096 token context window, it supports multilingual. For self-hosted inference, RTX 4060 delivers optimal throughput at $209/month.
Architecture Details
Memory Requirements
BF16 Weights
4.6 GB
FP8 Weights
2.3 GB
INT4 Weights
1.1 GB
GPU Compatibility Matrix
SeamlessM4T v2 Large is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
303.3 tok/s
Latency (ITL)
3.3ms
Est. TTFT
1ms
Cost/Month
$209
Cost/M Tokens
$0.26
BF16 · 1 GPU · vllm
100/100
score
Throughput
499.6 tok/s
Latency (ITL)
2.0ms
Est. TTFT
0ms
Cost/Month
$85
Cost/M Tokens
$0.07
BF16 · 1 GPU · vllm
90/100
score
Throughput
669.1 tok/s
Latency (ITL)
1.5ms
Est. TTFT
0ms
Cost/Month
$285
Cost/M Tokens
$0.16
Deployment Options
API Deployment
No API pricing available
Single GPU
RTX 4060
$209/mo
Min VRAM: 2 GB
Multi-GPU
RTX 4060
303.3 tok/s
Best available config
API Pricing Comparison
No API pricing data available for this model.
Performance Estimates
Throughput by GPU
VRAM Breakdown (RTX 4060, BF16)
Precision Impact
bf16
4.6 GB
weights/GPU
~303.3 tok/s
fp8
2.3 GB
weights/GPU
int4
1.1 GB
weights/GPU
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy SeamlessM4T v2 Large
Self-Hosted Infrastructure
Similar Models
Qwen 2 VL 2B
2.2B params · dense
Quality: 50
Gemma 1.1 2B
2.5B params · dense
Quality: 50
Gemma 3 2B
2B params · dense
Quality: 42
Gemma 2 2B
2.6B params · dense
Quality: 44
RecurrentGemma 2B
2.7B params · dense
Quality: 50
Frequently Asked Questions
How much VRAM does SeamlessM4T v2 Large need for inference?
SeamlessM4T v2 Large requires approximately 4.6 GB of VRAM at BF16 precision, 2.3 GB at FP8, or 1.1 GB at INT4 quantization. Additional VRAM is needed for KV-cache (98304 bytes per token) and activations (~0.30 GB).
What is the best GPU for SeamlessM4T v2 Large?
The top recommended GPU for SeamlessM4T v2 Large is the RTX 4060 using BF16 precision. It achieves approximately 303.3 tokens/sec at an estimated cost of $209/month ($0.26/M tokens). Score: 100/100.
How much does SeamlessM4T v2 Large inference cost?
SeamlessM4T v2 Large inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.