FitMyLLM
DeepSeek/Dense

DeepSeekDeepSeek Coder 1.3B

DeepSeek's tiny coder. Fast code completion on any hardware.

coding
1.3B
Parameters
16K
Context length
8
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2023-11-02
Layers
24
KV Heads
16
Head Dim
128
Family
deepseek

Quantization Options

QuantBitsVRAMQuality
Q4_K_M4.891.3 GBgood
Q5_K_S5.571.4 GBgood
Q5_K_M5.71.4 GBgood
Q6_K6.561.6 GBexcellent
Q8_08.51.9 GBlossless
FP16163.1 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 1.3B NOW

Rent on RunPod →Or Vast.ai →

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

Community Ratings

Loading ratings...

Benchmarks (8)

MBPP47.9
BBH40.0
HumanEval25.6
IFEval17.5
MUSR2.2
MMLU-PRO1.4
MATH0.0
GPQA0.0

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run deepseek-coder:1.3b-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
HuggingFaceOllama LibraryGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Quadro FX 5600
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro FX 5600 Mac Edition
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Tesla C870
2 GB VRAM • 76.8 GB/s
NVIDIA
NVIDIA Tesla D870
2 GB VRAM • 76.8 GB/s
NVIDIA
NVIDIA Tesla S870
2 GB VRAM • 76.8 GB/s
NVIDIA
NVIDIA Quadro CX
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro FX 4800
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 230 OEM
2 GB VRAM • 24 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 440 OEM
2 GB VRAM • 43.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 460M
2 GB VRAM • 60 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 470M
2 GB VRAM • 72 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 480
2 GB VRAM • 177.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 580
2 GB VRAM • 192.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 545
2 GB VRAM • 38.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 560M
2 GB VRAM • 60 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 570M
2 GB VRAM • 72 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 580 Rev. 2
2 GB VRAM • 192.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 590
2 GB VRAM • 164 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GT 640 OEM Rebrand
2 GB VRAM • 38.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 670M
2 GB VRAM • 72 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 760 OEM Rebrand
2 GB VRAM • 179.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 260 OEM
2 GB VRAM • 112.9 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro 4000 Mac Edition
2 GB VRAM • 89.9 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
AMD FireGL V8650
2 GB VRAM • 111 GB/s
AMD
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 285 X2
2 GB VRAM • 148 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 480M
2 GB VRAM • 77 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro 5000M
2 GB VRAM • 77 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
AMD Radeon HD 6950
2 GB VRAM • 160 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon HD 6970
2 GB VRAM • 176 GB/s
AMD
AmazonNeweggeBayPCPartPicker
Intel Aubrey Isle
2 GB VRAM • 154 GB/s
INTEL
AmazonNeweggeBayPCPartPicker

Find the best GPU for DeepSeek Coder 1.3B

Build Hardware for DeepSeek Coder 1.3B

Model Card

View on HuggingFace

DeepSeek's tiny coder. Fast code completion on any hardware.

▸ SPEC SHEET

DeepSeek Coder 1.3B — 1.3B Dense.

▸ SPECIFICATIONS
PARAMETERS
1.3B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
16K tokens
CAPABILITIES
coding
RELEASE DATE
2023-11-02
PROVIDER
DeepSeek
FAMILY
deepseek
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.891.3 GB94%
Q5_K_S5.571.4 GB96%
Q5_K_M5.71.4 GB96%
Q6_K6.561.6 GB97%
Q8_08.51.9 GB100%
FP16163.1 GB100%
§ 01BENCHMARK SCORES
HumanEval25.6
MMLU-PRO1.4
MATH0.0
IFEval17.5
BBH40.0
GPQA0.0
MUSR2.2
MBPP47.9
§ 02RUN COMMAND

Run DeepSeek Coder 1.3B locally with Ollama — needs 1.3 GB VRAM at Q4_K_M:

$ollama run deepseek-coder:1.3b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
NVIDIA Quadro FX 5600
2 GB · 76.8 GB/s
NVIDIA Quadro FX 5600 Mac Edition
2 GB · 76.8 GB/s
NVIDIA Tesla C870
2 GB · 76.8 GB/s
NVIDIA Tesla D870
2 GB · 76.8 GB/s
NVIDIA Tesla S870
2 GB · 76.8 GB/s
NVIDIA Quadro CX
2 GB · 76.8 GB/s
NVIDIA Quadro FX 4800
2 GB · 76.8 GB/s
NVIDIA GeForce GT 230 OEM
2 GB · 24 GB/s
NVIDIA GeForce GT 440 OEM
2 GB · 43.2 GB/s
NVIDIA GeForce GTX 460M
2 GB · 60 GB/s
NVIDIA GeForce GTX 470M
2 GB · 72 GB/s
NVIDIA GeForce GTX 480
2 GB · 177.4 GB/s
NVIDIA GeForce GTX 580
2 GB · 192.4 GB/s
NVIDIA GeForce GT 545
2 GB · 38.4 GB/s
NVIDIA GeForce GTX 560M
2 GB · 60 GB/s