IBM
Granite 4.1 8B
Actual
112.2KDescargas184Me gustaApr 2026Publicado131K tokensContextoApache 2.0Licencia58 BuenoCalidad
Granite 4.1 8B (8B parameters) requires approximately 9.1 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 11 GB of VRAM.
Comenzar
— copia y pega para ejecutar en localCopy-paste commands to run Granite 4.1 8B on your machine.
Run
ollama run granite4.1:8bQuick specs
Parameters8B
Architecturedense
Context131K tokens
Modalitytext
Min RAM3.1 GB
Rec. RAM4.9 GB (Q4_K_M)
LicenseApache 2.0
FamilyGranite
✓ Code✓ Chat✓ RAG
About this model
- •Dense decoder-only 8B — comfortable on 12-16 GB GPUs at Q8/FP8
- •Apache 2.0 license for commercial RAG and assistant use
- •Reported to match/beat Granite 4.0-H-Small 32B-A9B MoE
- •128K context for long-document retrieval
Modelos relacionados
Selecciones rápidas
Mejor hardware
Mejores opciones para Granite 4.1 8B
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 | 3.1 GB | Low | — |
Q3_K_S | 3 | 3.9 GB | Low | — |
NVFP4 | 4 | 4.5 GB | Medium | — |
Q4_K_M | 4 | 4.9 GB | Medium | — |
Q5_K_M | 5 | 5.8 GB | High | — |
Q6_K | 6 | 6.6 GB | High | — |
Q8_0 | 8 | 8.6 GB | Very High | — |
F16 | 16 | 16.4 GB | Maximum | — |
Compatibilidad de hardware
Estimaciones de encaje en todo el hardware
Computing compatibility...
Desglose de memoria
Reference: RTX 2060 6GB
Weights4.9 GB
KV Cache2.4 GB
Runtime1.2 GB
Headroom0.6 GB
Preguntas frecuentes
FAQ — Granite 4.1 8B
Ver también