Alibaba
Qwen 3.5 27B
Frontera
Jun 2025Publicado131K tokensContextoApache 2.0Licencia99 ExcepcionalCalidad
Qwen 3.5 27B (27B parameters) requires approximately 21.4 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 25 GB of VRAM.
Comenzar
— copia y pega para ejecutar en localCopy-paste commands to run Qwen 3.5 27B on your machine.
Run
ollama run qwen3.5:27bQuick specs
Parameters27B
Architecturedense
Context131K tokens
Modalitytext
Min RAM10.5 GB
Rec. RAM16.5 GB (Q4_K_M)
LicenseApache 2.0
FamilyQwen
✓ Code✓ Chat✓ Reasoning✓ RAG
About this model
- •Top-tier dense model quality — competitive with much larger models
- •Fits on RTX 4090 (24 GB) at Q4_K_M with room for context
- •Excellent instruction following and structured output generation
Modelos relacionados
Selecciones rápidas
Mejor hardware
Mejores opciones para Qwen 3.5 27B
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 | 10.5 GB | Low | — |
Q3_K_S | 3 | 13.2 GB | Low | — |
NVFP4 | 4 | 15.1 GB | Medium | — |
Q4_K_M | 4 | 16.5 GB | Medium | — |
Q5_K_M | 5 | 19.4 GB | High | — |
Q6_K | 6 | 22.1 GB | High | — |
Q8_0 | 8 | 28.9 GB | Very High | — |
F16 | 16 | 55.4 GB | Maximum | — |
Quality benchmarks
Qwen 3.5 27B benchmark scores
Coding
SWE-bench Verified72.4%
HumanEval+—
Aider Polyglot—
LiveCodeBench80.7%
Reasoning
MMLU-Pro86.1%
GPQA Diamond85.5%
MATH-50094.5%
ARC Challenge—
General
Chatbot Arena—
IFEval95.0%
Source: official · 2025-07-14
Compatibilidad de hardware
Estimaciones de encaje en todo el hardware
Computing compatibility...
Desglose de memoria
Reference: RTX 2060 6GB
Weights16.5 GB
KV Cache3.2 GB
Runtime1.2 GB
Headroom0.6 GB
Preguntas frecuentes
FAQ — Qwen 3.5 27B
Ver también