BigCode
StarCoder 15B
Legacy
24.4KDescargas3.0KMe gustaMay 2023Publicado8K tokensContextoApache 2.0Licencia60 BuenoCalidad
StarCoder 15B (15B parameters) requires approximately 27.2 GB of VRAM with Q5_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 32 GB of VRAM.
Comenzar
— copia y pega para ejecutar en localCopy-paste commands to run StarCoder 15B on your machine.
Run
lms load starcoder && lms server startQuick specs
Parameters15B
Architecturedense
Context8K tokens
Modalitycode
Min RAM5.9 GB
Rec. RAM10.8 GB (Q5_K_M)
LicenseApache 2.0
FamilyStarCoder
✓ Code✓ Reasoning
About this model
Modelos relacionados
Selecciones rápidas
Mejor hardware
Mejores opciones para StarCoder 15B
Ejecutar este modelo
Opciones de cuantización
Estimaciones de VRAM por nivel de cuantización
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | — |
Q3_K_S | 3 | 7.4 GB | Low | — |
NVFP4 | 4 | 8.4 GB | Medium | — |
Q4_K_M | 4 | 9.2 GB | Medium | — |
Q5_K_M | 5 | 10.8 GB | High | — |
Q6_K | 6 | 12.3 GB | High | — |
Q8_0 | 8 | 16.1 GB | Very High | — |
F16 | 16 | 30.7 GB | Maximum | — |
Quality benchmarks
StarCoder 15B benchmark scores
Coding
SWE-bench Verified—
HumanEval+33.6%
Aider Polyglot—
LiveCodeBench—
Source: official · 2023-05-04
Compatibilidad de hardware
Estimaciones de encaje en todo el hardware
Computing compatibility...
Desglose de memoria
Reference: RTX 2060 6GB
Weights10.8 GB
KV Cache14.6 GB
Runtime1.2 GB
Headroom0.6 GB
Preguntas frecuentes
FAQ — StarCoder 15B
Ver también