Mradermacher
EXAONE 3.5 7.8B Instruct i1
可用数据有限 — 部分规格可能不完整或为估算值。
0K tokens上下文Unknown许可证4 入门质量
EXAONE 3.5 7.8B Instruct i1 (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
Parameters7.8B
Architecturedense
Context0K tokens
Modalitytext
Min RAM3 GB
Rec. RAM4.8 GB (Q4_K_M)
LicenseUnknown
FamilyUnknown
✓ Chat
相关模型
快速推荐
最佳硬件
EXAONE 3.5 7.8B Instruct i1 的最佳选择
运行此模型
量化选项
各量化级别的 VRAM 估算
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 | — |
硬件兼容性
全部硬件的适配估算
Computing compatibility...
内存详细分析
Reference: RTX 2060 6GB
Weights4.8 GB
KV Cache0.9 GB
Runtime0.9 GB
Headroom0.6 GB
常见问题
FAQ — EXAONE 3.5 7.8B Instruct i1
另请参阅