Will It Run AI

MistralMistral

Mistral Nemo 12B

当前
684.0K下载量1.7K点赞Jul 2024发布日期128K tokens上下文Apache 2.0许可证32 基础质量

Mistral Nemo 12B (12B parameters) requires approximately 11.6 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 14 GB of VRAM.

快速开始

— 复制粘贴即可本地运行

Copy-paste commands to run Mistral Nemo 12B on your machine.

Run

ollama run mistral-nemo

Quick specs

Parameters12B
Architecturedense
Context128K tokens
Modalitytext
Min RAM4.7 GB
Rec. RAM7.3 GB (Q4_K_M)
LicenseApache 2.0
FamilyMistral
Chat

About this model

The Mistral-Nemo-Instruct-2407 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-Nemo-Base-2407. Trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.

  • Released under the Apache 2 License
  • Pre-trained and instructed versions
  • Trained with a 128k context window
  • Trained on a large proportion of multilingual and code data
  • Drop-in replacement of Mistral 7B

相关模型

你的硬件

检测中...

快速推荐

最佳硬件

Mistral Nemo 12B 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

QuantBitsVRAMQualityFit
Q2_K
2
4.7 GB
Low
Q3_K_S
3
5.9 GB
Low
NVFP4
4
6.7 GB
Medium
Q4_K_M
4
7.3 GB
Medium
Q5_K_M
5
8.6 GB
High
Q6_K
6
9.8 GB
High
Q8_0
8
12.8 GB
Very High
F16
16
24.6 GB
Maximum

Quality benchmarks

Mistral Nemo 12B benchmark scores

Benchmark verified

Reasoning

MMLU-Pro68.0%
GPQA Diamond5.4%
MATH-50012.7%
ARC Challenge

General

Chatbot Arena
IFEval63.8%

Source: official · 2024-07-18

硬件兼容性

全部硬件的适配估算

打开计算器

Computing compatibility...

内存详细分析

Reference: RTX 2060 6GB

Weights7.3 GB
KV Cache2.4 GB
Runtime1.2 GB
Headroom0.6 GB

常见问题

FAQ — Mistral Nemo 12B

另请参阅