FitMyLLM
BigCode/Dense

BigCodeStarCoder2 15B

StarCoder2 15B — top open code model for its size, extensive language support.

coding
15B
Parameters
16K
Context length
9
Benchmarks
10
Quantizations
0
Architecture
Dense
Released
2024-02-28
Layers
40
KV Heads
4
Head Dim
128
Family
starcoder

Quantization Options

QuantBitsVRAMQuality
Q3_K_M48.0 GBlow
Q3_K_L4.38.6 GBmoderate
IQ4_XS4.468.9 GBmoderate
Q4_K_S4.679.2 GBmoderate
Q4_K_M4.899.7 GBgood
Q5_K_S5.5710.9 GBgood
Q5_K_M5.711.2 GBgood
Q6_K6.5612.8 GBexcellent
Q8_08.516.4 GBlossless
FP161630.5 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 STARCODER2 15B 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 (9)

MBPP65.1
HumanEval60.4
BigCodeBench37.6
IFEval27.8
BBH20.4
MMLU-PRO15.0
MATH6.0
GPQA3.1
MUSR2.9

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run starcoder2:15b-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 RTX 3080 10GB
10 GB VRAM • 760 GB/s
NVIDIA
$429
AmazonNeweggeBayPCPartPicker
Intel Arc B570
10 GB VRAM • 456 GB/s
INTEL
$219
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce RTX 3080
10 GB VRAM • 760 GB/s
NVIDIA
$699
AmazonNeweggeBayPCPartPicker
AMD Radeon RX 6700
10 GB VRAM • 320 GB/s
AMD
$299
AmazonNeweggeBayPCPartPicker
AMD Radeon RX 6700M
10 GB VRAM • 320 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon RX 6750 GRE 10 GB
10 GB VRAM • 320 GB/s
AMD
$229
AmazonNeweggeBayPCPartPicker
NVIDIA P102-101
10 GB VRAM • 320 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
AMD Xbox Series X GPU
10 GB VRAM • 560 GB/s
AMD
AmazonNeweggeBayPCPartPicker
NVIDIA CMP 170HX 10 GB
10 GB VRAM • 1560 GB/s
NVIDIA
NVIDIA CMP 50HX
10 GB VRAM • 560 GB/s
NVIDIA
NVIDIA CMP 90HX
10 GB VRAM • 760 GB/s
NVIDIA
AMD Xbox Series X 6nm GPU
10 GB VRAM • 560 GB/s
AMD
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 2080 Ti
11 GB VRAM • 616 GB/s
NVIDIA
$350
AmazonNeweggeBayPCPartPicker
NVIDIA GTX 1080 Ti
11 GB VRAM • 484 GB/s
NVIDIA
$200
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 1080 Ti
11 GB VRAM • 484 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce RTX 2080 Ti
11 GB VRAM • 616 GB/s
NVIDIA
$225
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 5070
12 GB VRAM • 672 GB/s
NVIDIA
$549
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 4070 Ti
12 GB VRAM • 504 GB/s
NVIDIA
$799
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 4070 SUPER
12 GB VRAM • 504 GB/s
NVIDIA
$599
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 4070
12 GB VRAM • 504 GB/s
NVIDIA
$549
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 3080 Ti
12 GB VRAM • 912 GB/s
NVIDIA
$550
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 3080 12GB
12 GB VRAM • 912 GB/s
NVIDIA
$599
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 3060 12GB
12 GB VRAM • 360 GB/s
NVIDIA
$329
AmazonNeweggeBayPCPartPicker
AMD RX 7700 XT
12 GB VRAM • 432 GB/s
AMD
$449
AmazonNeweggeBayPCPartPicker
AMD RX 6700 XT
12 GB VRAM • 384 GB/s
AMD
$344
AmazonNeweggeBayPCPartPicker
AMD RX 6750 XT
12 GB VRAM • 432 GB/s
AMD
$299
AmazonNeweggeBayPCPartPicker
Intel Arc B580
12 GB VRAM • 456 GB/s
INTEL
$249
AmazonNeweggeBayPCPartPicker
NVIDIA Tesla K40c
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K40d
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K40m
12 GB VRAM • 288 GB/s
NVIDIA

Find the best GPU for StarCoder2 15B

Build Hardware for StarCoder2 15B

Model Card

View on HuggingFace

StarCoder2 15B — top open code model for its size, extensive language support.

▸ SPEC SHEET

StarCoder2 15B — 15B Dense.

▸ SPECIFICATIONS
PARAMETERS
15B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
16K tokens
CAPABILITIES
coding
RELEASE DATE
2024-02-28
PROVIDER
BigCode
FAMILY
starcoder
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q3_K_M48.0 GB88%
Q3_K_L4.38.6 GB90%
IQ4_XS4.468.9 GB92%
Q4_K_S4.679.2 GB93%
Q4_K_M4.899.7 GB94%
Q5_K_S5.5710.9 GB96%
Q5_K_M5.711.2 GB96%
Q6_K6.5612.8 GB97%
Q8_08.516.4 GB100%
FP161630.5 GB100%
§ 01BENCHMARK SCORES
HumanEval60.4
MMLU-PRO15.0
MATH6.0
IFEval27.8
BBH20.4
GPQA3.1
MUSR2.9
MBPP65.1
BigCodeBench37.6
§ 02RUN COMMAND

Run StarCoder2 15B locally with Ollama — needs 9.7 GB VRAM at Q4_K_M:

$ollama run starcoder2:15b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
NVIDIA RTX 3080 10GB
10 GB · 760 GB/s
Intel Arc B570
10 GB · 456 GB/s
NVIDIA GeForce RTX 3080
10 GB · 760 GB/s
AMD Radeon RX 6700
10 GB · 320 GB/s
AMD Radeon RX 6700M
10 GB · 320 GB/s
AMD Radeon RX 6750 GRE 10 GB
10 GB · 320 GB/s
NVIDIA P102-101
10 GB · 320 GB/s
AMD Xbox Series X GPU
10 GB · 560 GB/s
NVIDIA CMP 170HX 10 GB
10 GB · 1560 GB/s
NVIDIA CMP 50HX
10 GB · 560 GB/s
NVIDIA CMP 90HX
10 GB · 760 GB/s
AMD Xbox Series X 6nm GPU
10 GB · 560 GB/s
NVIDIA RTX 2080 Ti
11 GB · 616 GB/s
NVIDIA GTX 1080 Ti
11 GB · 484 GB/s
NVIDIA GeForce GTX 1080 Ti
11 GB · 484 GB/s