~/model/huggingfacebigcode/starcoder2-15b
BigCode

StarCoder2 15B

BigCode's 15B code reference. Strong fill-in-the-middle; the open StarCoder lineage continues here.

Parameters
15B
Family
BigCode
Context
16K tokens
FP16 weights
30GB
// where you can run it
starcoder2:15bLM StudiovLLMMLXoMLX
// hugging face stats (cached daily)
16K downloads · 670 likes · license: bigcode-openrail-m · updated 1 year ago

What you need to run this.

$ ./vrambudget --model starcoder2-15b --by quant
FP1630 GB
RTX A600048 GB · fitsRTX 6000 Ada48 GB · fitsL40S48 GB · fitsRadeon Pro W790048 GB · fits
Q8_016 GB
RTX 309024 GB · fitsRTX 3090 Ti24 GB · fitsRTX 409024 GB · fitsRX 7900 XTX24 GB · fits
Q6_K12 GB
RTX 309024 GB · fitsRTX 3090 Ti24 GB · fitsRTX 409024 GB · fitsRX 7900 XTX24 GB · fits
Q5_K_M10 GB
RTX 4060 Ti 16GB16 GB · fitsRTX 4070 Ti Super16 GB · fitsRTX 408016 GB · fitsRTX 4080 Super16 GB · fits
Q4_K_M8.4 GB
RTX 3060 12GB12 GB · fitsRTX 3080 Ti12 GB · fitsRTX 407012 GB · fitsRTX 4070 Super12 GB · fits

// budgets shown at ctx 8K, concurrency 1, 15% safety headroom. Tune in the calculator →

Alternatives at this size.

$ grep --params similar catalog.json
$ similarPhi-414.7BMicrosoft$ similargpt-oss 20B20.9BOpenAI$ similarQwen 3.5 9B9BAlibaba$ similarGemma 2 9B9BGoogle

Discussion.

$ gh discussion list

// sign in with github to leave a comment. threads live in the repo's discussions tab.