Alibaba
Qwen 2.5 VL 72B
Frontera
370.7KDescargas622Me gustaJan 2025Publicado33K tokensContextoApache 2.0Licencia94 ExcepcionalCalidad
Qwen 2.5 VL 72B (72B parameters) requires approximately 50.3 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 58 GB of VRAM.
Comenzar
— copia y pega para ejecutar en localCopy-paste commands to run Qwen 2.5 VL 72B on your machine.
Run
lms load Qwen2.5-VL-72B-Instruct && lms server startQuick specs
Parameters72B
Architecturedense
Context33K tokens
Modalitytext+vision
Min RAM28.1 GB
Rec. RAM43.9 GB (Q4_K_M)
LicenseApache 2.0
FamilyQwen
✓ Vision✓ Chat✓ Reasoning
About this model
- •Understand things visually: Qwen2.5-VL is not only proficient in recognizing common objects such as flowers, birds, fish, and insects, but it is...
- •Being agentic: Qwen2.5-VL directly plays as a visual agent that can reason and dynamically direct tools, which is capable of computer use and...
- •Understanding long videos and capturing events: Qwen2.5-VL can comprehend videos of over 1 hour, and this time it has a new ability of cpaturing...
- •Capable of visual localization in different formats: Qwen2.5-VL can accurately localize objects in an image by generating bounding boxes or...
- •Generating structured outputs: for data like scans of invoices, forms, tables, etc. Qwen2.5-VL supports structured outputs of their contents,...
Modelos relacionados
Selecciones rápidas
Mejor hardware
Mejores opciones para Qwen 2.5 VL 72B
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 | 28.1 GB | Low | — |
Q3_K_S | 3 | 35.3 GB | Low | — |
NVFP4 | 4 | 40.3 GB | Medium | — |
Q4_K_M | 4 | 43.9 GB | Medium | — |
Q5_K_M | 5 | 51.8 GB | High | — |
Q6_K | 6 | 59.0 GB | High | — |
Q8_0 | 8 | 77.0 GB | Very High | — |
F16 | 16 | 147.6 GB | Maximum | — |
Quality benchmarks
Qwen 2.5 VL 72B benchmark scores
Reasoning
MMLU-Pro70.2%
GPQA Diamond—
MATH-500—
ARC Challenge—
Source: community · 2025-01-26
Compatibilidad de hardware
Estimaciones de encaje en todo el hardware
Computing compatibility...
Desglose de memoria
Reference: RTX 2060 6GB
Weights43.9 GB
KV Cache4.9 GB
Runtime0.9 GB
Headroom0.6 GB
Preguntas frecuentes
FAQ — Qwen 2.5 VL 72B
Ver también