DeepSeek R1 Distill 32B
DeepSeek · dense · 32.8B parameters · 131,072 context
Parameters
32.8B
Context Window
128K tokens
Architecture
Dense
Best GPU
H20
Cheapest API
$0.50/M
Quality Score
88/100
Intelligence Brief
DeepSeek R1 Distill 32B is a 32.8B parameter DENSE model from DeepSeek, featuring Grouped Query Attention (GQA) with 64 layers and 5,120 hidden dimensions. With a 131,072 token context window, it supports tools, structured output, code, math, multilingual, reasoning. On standardized benchmarks, it achieves MMLU 90.8, HumanEval 71.7, GSM8K 97.3. The most cost-effective API deployment is via fireworks at $0.50/M output tokens. For self-hosted inference, H20 delivers optimal throughput at $940/month.
Architecture Details
Memory Requirements
BF16 Weights
65.6 GB
FP8 Weights
32.8 GB
INT4 Weights
16.4 GB
GPU Compatibility Matrix
DeepSeek R1 Distill 32B 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
854.4 tok/s
Latency (ITL)
1.2ms
Est. TTFT
0ms
Cost/Month
$1794
Cost/M Tokens
$0.80
Deployment Options
API Deployment
fireworks
$0.50/M
output tokens
Single GPU
H20
$940/mo
Min VRAM: 33 GB
Multi-GPU
RTX A6000 x2
111.3 tok/s
TP· $930/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| fireworks | $0.50 | $0.50 | Cheapest |
| together | $0.60 | $0.60 |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| fireworksBest Value | $0.50 | $0.50 | $5 |
| together | $0.60 | $0.60 | $6 |
Cost per 1,000 Requests
Short (500 tok)
$0.35
via fireworks
Medium (2K tok)
$1.40
via fireworks
Long (8K tok)
$5.00
via fireworks
Performance Estimates
Throughput by GPU
VRAM Breakdown (H20, FP8)
Precision Impact
bf16
65.6 GB
weights/GPU
fp8
32.8 GB
weights/GPU
~1.0K tok/s
int4
16.4 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy DeepSeek R1 Distill 32B
Self-Hosted Infrastructure
Similar Models
DeepSeek R1 Distill 14B
14.8B params · dense
Quality: 88
from $0.30/M
DeepSeek R1 Distill 70B
70.6B params · dense
Quality: 88
from $0.88/M
Qwen 3 32B
32.8B params · dense
Quality: 74
from $0.80/M
DeepSeek Coder 33B
33B params · dense
Quality: 50
from $0.80/M
Vicuna 33B
33B params · dense
Quality: 50
Frequently Asked Questions
How much VRAM does DeepSeek R1 Distill 32B need for inference?
DeepSeek R1 Distill 32B requires approximately 65.6 GB of VRAM at BF16 precision, 32.8 GB at FP8, or 16.4 GB at INT4 quantization. Additional VRAM is needed for KV-cache (262144 bytes per token) and activations (~2.00 GB).
What is the best GPU for DeepSeek R1 Distill 32B?
The top recommended GPU for DeepSeek R1 Distill 32B 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 R1 Distill 32B inference cost?
DeepSeek R1 Distill 32B API inference starts from $0.50/M input tokens and $0.50/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.