Bingsu
exaone 3.0 7.8b it (7.800000190734863B parameters) requires approximately 7.2 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 9 GB of VRAM.
Quick specs
Related models
Quick picks
Best hardware
Run this model
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.0 GB | Low | — |
Q3_K_S | 3 | 3.8 GB | Low | — |
NVFP4 | 4 | 4.4 GB | Medium | — |
Q4_K_M | 4 | 4.8 GB | Medium | — |
Q5_K_M | 5 | 5.6 GB | High | — |
Q6_K | 6 | 6.4 GB | High | — |
Q8_0 | 8 | 8.3 GB | Very High | — |
F16 | 16 | 16.0 GB | Maximum | — |
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
exaone 3.0 7.8b it (7.800000190734863B parameters) requires approximately 7.2 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, Intel Arc A580 8GB can run exaone 3.0 7.8b it with a compatibility score of 52/100. It provides 8 GB of memory and achieves approximately 52.7 tokens per second.
The recommended quantization for exaone 3.0 7.8b it is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for exaone 3.0 7.8b it: RTX 3080 10GB (score: 57/100), RTX 2080 Ti 11GB (score: 56/100), RTX 3080 Ti 12GB (score: 56/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, exaone 3.0 7.8b it is well-suited for chat. It was designed with these use cases in mind.
See also
