👁 LMSYS
LMSYS
Vicuna 7B
Legacy
89.5KDownloads401LikesMar 2023Released4K tokensContextLlama 2 CommunityLicense5 EntryQuality
Vicuna 7B (7B parameters) requires approximately 13.9 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 16 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run Vicuna 7B on your machine.
Run
ollama run vicunaQuick specs
Parameters7B
Architecturedense
Context4K tokens
Modalitytext
Min RAM2.7 GB
Rec. RAM4.3 GB (Q4_K_M)
LicenseLlama 2 Community
FamilyVicuna
✓ Chat
About this model
- •Developed by:: LMSYS
- •Model type:: An auto-regressive language model based on the transformer architecture
- •License:: Llama 2 Community License Agreement
- •Finetuned from model:: Llama 2
Related models
Your hardware
Detecting...
Quick picks
Best hardware
Top picks for Vicuna 7B
Run this model
Quantization options
VRAM estimates by quant level
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
Vicuna 7B benchmark scores
Reasoning
MMLU-Pro12.7%
GPQA Diamond1.1%
MATH-5001.4%
ARC Challenge74.1%
General
Chatbot Arena—
IFEval23.5%
Source: community · 2023-07-29
Hardware compatibility
Fit estimates across all hardware
Computing compatibility...
Memory breakdown
Reference: RTX 2060 6GB
Weights4.3 GB
KV Cache7.8 GB
Runtime1.2 GB
Headroom0.6 GB
Frequently asked questions
FAQ — Vicuna 7B
See also