Updated minutes ago
Llama 3.2 90B Vision Instruct
Meta · dense · 88.8B parameters · 131,072 context
Quality84.0
Architecture Details
TypeDENSE
Total Parameters88.8B
Active Parameters88.8B
Layers80
Hidden Dimension8,192
Attention Heads64
KV Heads8
Head Dimension128
Vocab Size128,256
Memory Requirements
BF16 Weights
177.6 GB
FP8 Weights
88.8 GB
INT4 Weights
44.4 GB
KV-Cache per Token655360 bytes
Activation Estimate4.00 GB
Fits on (single-node)
B200 SXM FP8B100 SXM FP8GB200 NVL72 (per GPU) FP8GB300 NVL72 (per GPU) FP8H200 SXM FP8H100 SXM INT4H100 PCIe INT4H100 NVL INT4
GPU Recommendations
B200 SXMoptimal
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
560.0 tok/s
Cost/Month
$4261
Cost/M Tokens
$2.90
H200 SXMoptimal
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
452.2 tok/s
Cost/Month
$2553
Cost/M Tokens
$2.15
H100 SXMoptimal
FP8 · 2 GPUs · tensorrt-llm
100/100
score
Throughput
560.0 tok/s
Cost/Month
$3587
Cost/M Tokens
$2.44
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| together | $1.20 | $1.20 | Cheapest |
Quality Benchmarks
MMLU86.0
HumanEval58.0
GSM8K92.0
MT-Bench86.0
Capabilities
Features
✓ Tool Use✓ Vision✓ Code✓ Math✗ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
vllmsglangtgitensorrt-llm
Supported Precisions
BF16 (default)FP8INT4