OpenChat
OpenChat 7B
Legacy
2.0KDescargas278Me gustaDec 2023Publicado8K tokensContextoApache 2.0Licencia9 EntradaCalidad
OpenChat 7B (7B parameters) requires approximately 8.0 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 10 GB of VRAM.
Comenzar
— copia y pega para ejecutar en localCopy-paste commands to run OpenChat 7B on your machine.
Run
ollama run openchatQuick specs
Parameters7B
Architecturedense
Context8K tokens
Modalitytext
Min RAM2.7 GB
Rec. RAM4.3 GB (Q4_K_M)
LicenseApache 2.0
FamilyOpenChat
✓ Chat
About this model
- •Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general
- •After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric
- •The output format should look as follows: "Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)"
- •Please do not generate any other opening, closing, and explanations
Selecciones rápidas
Mejor hardware
Mejores opciones para OpenChat 7B
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 | 2.7 GB | Low | — |
Q3_K_S | 3 | 3.4 GB | Low | — |
NVFP4 | 4 | 3.9 GB | Medium | — |
Q4_K_M | 4 | 4.3 GB | Medium | — |
Q5_K_M | 5 | 5.0 GB | High | — |
Q6_K | 6 | 5.7 GB | High | — |
Q8_0 | 8 | 7.5 GB | Very High | — |
F16 | 16 | 14.3 GB | Maximum | — |
Quality benchmarks
OpenChat 7B benchmark scores
Reasoning
MMLU-Pro23.8%
GPQA Diamond6.8%
MATH-5007.9%
ARC Challenge62.0%
General
Chatbot Arena—
IFEval60.4%
Source: community · 2024-01-06
Compatibilidad de hardware
Estimaciones de encaje en todo el hardware
Computing compatibility...
Desglose de memoria
Reference: RTX 2060 6GB
Weights4.3 GB
KV Cache2.0 GB
Runtime1.2 GB
Headroom0.6 GB
Preguntas frecuentes
FAQ — OpenChat 7B
Ver también