Will It Run AI

CohereCohere

Command R+ 104B

当前
1.8K下载量285点赞Apr 2024发布日期131K tokens上下文CC-BY-NC-4.0许可证43 基础质量

Command R+ 104B (104B parameters) requires approximately 68.4 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 79 GB of VRAM.

快速开始

— 复制粘贴即可本地运行

Copy-paste commands to run Command R+ 104B on your machine.

Run

ollama run command-r-plus

Quick specs

Parameters104B
Architecturedense
Context131K tokens
Modalitytext
Min RAM40.6 GB
Rec. RAM63.4 GB (Q4_K_M)
LicenseCC-BY-NC-4.0
FamilyCommand
Chat Reasoning RAG

About this model

Command R+ is Cohere's most capable open-weight model for enterprise RAG workloads. Offers superior long-context reasoning, multi-step tool use, and grounded generation with citations across 10 languages.

相关模型

你的硬件

检测中...

快速推荐

最佳硬件

Command R+ 104B 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
40.6 GB
Low
Q3_K_S
3
51.0 GB
Low
NVFP4
4
58.2 GB
Medium
Q4_K_M
4
63.4 GB
Medium
Q5_K_M
5
74.9 GB
High
Q6_K
6
85.3 GB
High
Q8_0
8
111.3 GB
Very High
F16
16
213.2 GB
Maximum

Quality benchmarks

Command R+ 104B benchmark scores

Benchmark verified

Coding

SWE-bench Verified
HumanEval+74.4%
Aider Polyglot
LiveCodeBench

Reasoning

MMLU-Pro54.7%
GPQA Diamond13.4%
MATH-50046.0%
ARC Challenge

General

Chatbot Arena
IFEval60.0%

Source: official · 2024-04-04

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

Weights63.4 GB
KV Cache3.4 GB
Runtime0.9 GB
Headroom0.6 GB

常见问题

FAQ — Command R+ 104B

另请参阅