DeepSeek Coder 33B
DeepSeek · dense · 33B parameters · 16,384 context
Parameters
33B
Context Window
16K tokens
Architecture
Dense
Best GPU
H20
Cheapest API
$0.80/M
Intelligence Brief
DeepSeek Coder 33B is a 33B parameter DENSE model from DeepSeek, featuring Grouped Query Attention (GQA) with 62 layers and 7,168 hidden dimensions. With a 16,384 token context window, it supports code, math. The most cost-effective API deployment is via together at $0.80/M output tokens. For self-hosted inference, H20 delivers optimal throughput at $940/month.
Architecture Details
Memory Requirements
BF16 Weights
66.0 GB
FP8 Weights
33.0 GB
INT4 Weights
16.5 GB
GPU Compatibility Matrix
DeepSeek Coder 33B is compatible with 57% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
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
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
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
Deployment Options
API Deployment
together
$0.80/M
output tokens
Single GPU
H20
$940/mo
Min VRAM: 33 GB
Multi-GPU
RTX A6000 x2
110.6 tok/s
TP· $930/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| together | $0.80 | $0.80 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| togetherBest Value | $0.80 | $0.80 | $8 |
Cost per 1,000 Requests
Short (500 tok)
$0.56
via together
Medium (2K tok)
$2.24
via together
Long (8K tok)
$8.00
via together
Performance Estimates
Throughput by GPU
VRAM Breakdown (H20, FP8)
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
Supported Frameworks
Supported Precisions
Where to Deploy DeepSeek Coder 33B
Self-Hosted Infrastructure
Similar Models
Vicuna 33B
33B params · dense
Quality: 50
WizardCoder 33B
33B params · dense
Quality: 50
Grok-3 Mini
33B params · dense
Quality: 78
from $0.50/M
DeepSeek R1 Distill 32B
32.8B params · dense
Quality: 88
from $0.50/M
Qwen 3 32B
32.8B params · dense
Quality: 74
from $0.80/M
Frequently Asked Questions
How much VRAM does DeepSeek Coder 33B need for inference?
DeepSeek Coder 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 (253952 bytes per token) and activations (~1.80 GB).
What is the best GPU for DeepSeek Coder 33B?
The top recommended GPU for DeepSeek Coder 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 DeepSeek Coder 33B inference cost?
DeepSeek Coder 33B API inference starts from $0.80/M input tokens and $0.80/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.