DeepSeek/Dense

DeepSeekDeepSeek Coder 33B

DeepSeek Coder 33B — professional-grade code generation and completion.

coding
33B
Parameters
16K
Context length
7
Benchmarks
14
Quantizations
0
Architecture
Dense
Released
2023-11-02
Layers
62
KV Heads
8
Head Dim
128
Family
deepseek

Quantization Options

QuantBitsVRAMQuality
IQ3_XXS3.2513.9 GBlow
IQ3_XS3.514.9 GBlow
Q3_K_S3.6415.5 GBlow
IQ3_M3.7616.0 GBlow
Q3_K_M417.0 GBlow
Q3_K_L4.318.2 GBmoderate
IQ4_XS4.4618.9 GBmoderate
Q4_K_S4.6719.8 GBmoderate
Q4_K_M4.8920.7 GBgood
Q5_K_S5.5723.5 GBgood
Q5_K_M5.724.0 GBgood
Q6_K6.5627.5 GBexcellent
Q8_08.535.6 GBlossless
FP161666.5 GBlossless

Select your GPU above to see speed estimates and compatibility for each quantization.

READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN DEEPSEEK CODER 33B NOW

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (7)

HumanEval44.5
IFEval41.9
MMLU-PRO41.0
MATH17.1
BBH17.1
MUSR16.1
GPQA4.6

Run this model

Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run deepseek-coder:33b-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA RTX 4090
24 GB VRAM • 1008 GB/s
NVIDIA
$1599
NVIDIA RTX 3090 Ti
24 GB VRAM • 1008 GB/s
NVIDIA
$999
NVIDIA RTX 3090
24 GB VRAM • 936 GB/s
NVIDIA
$850
AMD RX 7900 XTX
24 GB VRAM • 960 GB/s
AMD
$999
Apple M4 Pro (24GB)
24 GB VRAM • 273 GB/s
APPLE
$1399
NVIDIA L4 24GB
24 GB VRAM • 300 GB/s
NVIDIA
$2500
NVIDIA A10 24GB
24 GB VRAM • 600 GB/s
NVIDIA
$3500
Apple M2 (24GB)
24 GB VRAM • 100 GB/s
APPLE
$999
Apple M3 (24GB)
24 GB VRAM • 100 GB/s
APPLE
$999
Apple M4 (24GB)
24 GB VRAM • 120 GB/s
APPLE
$699
NVIDIA Tesla M40 24 GB
24 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla P10
24 GB VRAM • 694 GB/s
NVIDIA
NVIDIA Tesla P40
24 GB VRAM • 347 GB/s
NVIDIA
NVIDIA Quadro RTX 6000
24 GB VRAM • 672 GB/s
NVIDIA
$4000
NVIDIA GeForce RTX 3090
24 GB VRAM • 936 GB/s
NVIDIA
$1499
NVIDIA A10 PCIe
24 GB VRAM • 600 GB/s
NVIDIA
NVIDIA A10G
24 GB VRAM • 600 GB/s
NVIDIA
NVIDIA RTX A5000
24 GB VRAM • 768 GB/s
NVIDIA
$2500
NVIDIA GeForce RTX 4090
24 GB VRAM • 1010 GB/s
NVIDIA
$1599
NVIDIA L40 CNX
24 GB VRAM • 864 GB/s
NVIDIA
$5000
NVIDIA L40G
24 GB VRAM • 864 GB/s
NVIDIA
$5000
NVIDIA A30 PCIe
24 GB VRAM • 933 GB/s
NVIDIA
NVIDIA A30X
24 GB VRAM • 1220 GB/s
NVIDIA

Find the best GPU for DeepSeek Coder 33B

Build Hardware for DeepSeek Coder 33B

DeepSeek Coder 33B — professional-grade code generation and completion.

▸ SPEC SHEET

DeepSeek Coder 33B33B Dense.

▸ SPECIFICATIONS
PARAMETERS
33B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
16K tokens
CAPABILITIES
coding
RELEASE DATE
2023-11-02
PROVIDER
DeepSeek
FAMILY
deepseek
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
IQ3_XXS3.2513.9 GB82%
IQ3_XS3.514.9 GB84%
Q3_K_S3.6415.5 GB85%
IQ3_M3.7616.0 GB86%
Q3_K_M417.0 GB88%
Q3_K_L4.318.2 GB90%
IQ4_XS4.4618.9 GB92%
Q4_K_S4.6719.8 GB93%
Q4_K_M4.8920.7 GB94%
Q5_K_S5.5723.5 GB96%
Q5_K_M5.724.0 GB96%
Q6_K6.5627.5 GB97%
Q8_08.535.6 GB100%
FP161666.5 GB100%
§ 01BENCHMARK SCORES
HumanEval44.5
MMLU-PRO41.0
MATH17.1
IFEval41.9
BBH17.1
GPQA4.6
MUSR16.1
§ 02RUN COMMAND

Run DeepSeek Coder 33B locally with Ollama — needs 20.7 GB VRAM at Q4_K_M:

$ollama run deepseek-coder:33b