Skip to content
Updated minutes ago
DeepSeek

DeepSeek LLM 67B

DeepSeek · dense · 67B parameters · 4,096 context

Quality
66.0

Architecture Details

TypeDENSE
Total Parameters67B
Active Parameters67B
Layers95
Hidden Dimension8,192
Attention Heads64
KV Heads8
Head Dimension128
Vocab Size102,400

Memory Requirements

BF16 Weights

134.0 GB

FP8 Weights

67.0 GB

INT4 Weights

33.5 GB

KV-Cache per Token655360 bytes
Activation Estimate2.50 GB

Fits on (single-node)

B200 SXM BF16B100 SXM BF16GB200 NVL72 (per GPU) BF16GB300 NVL72 (per GPU) BF16H200 SXM FP8H100 SXM FP8H100 PCIe FP8H100 NVL FP8

GPU Recommendations

H200 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

100/100

score

Throughput

560.0 tok/s

Cost/Month

$2553

Cost/M Tokens

$1.73

Use this config →
H100 NVLoptimal

FP8 · 1 GPU · tensorrt-llm

100/100

score

Throughput

491.7 tok/s

Cost/Month

$2932

Cost/M Tokens

$2.27

Use this config →
H20optimal

FP8 · 1 GPU · tensorrt-llm

100/100

score

Throughput

499.4 tok/s

Cost/Month

$940

Cost/M Tokens

$0.72

Use this config →

API Pricing Comparison

No API pricing data available for this model.

Quality Benchmarks

MMLU
71.3
HumanEval
42.0
GSM8K
72.0
MT-Bench
76.0

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgitensorrt-llm

Supported Precisions

BF16 (default)FP8INT4

Similar Models