Command R+ (104B) — VRAM, Speed & Local Setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

作者： Jakub Rusinowski · 最后更新： 2024年4月4日

Model library → Command R Family → Command R+ (104B)

Cohere's flagship model for complex enterprise RAG. Handles multi-hop retrieval, grounded citations, and complex tool orchestration. Outperforms GPT-4 Turbo on RAG benchmarks.

Command R+ (104B) needs about 64 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters	104 Billion
Context window	128,000
Architecture	Dense
Provider	Cohere
Licence	CC-BY-NC
Specified at	Q4_K_M
System RAM	128 GB
Record updated	2024-04-04

Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.

Licence

CC-BY-NC-4.0 — research / non-commercial only. Research / non-commercial only — this licence does NOT permit shipping a commercial product.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB). Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

Quant	Bits/weight	Weights	VRAM needed	Est. speed	Fit on 24 GB
Q2_K	2.63	34.2 GB	37.1 GB	~3 tok/s (est.)	Offloads to system RAM (slow)
Q3_K_M	3.41	44.3 GB	47.3 GB	~2 tok/s (est.)	Offloads to system RAM (slow)
Q4_K_M	4.83	62.8 GB	65.7 GB	—	Won't fit
Q5_K_M	5.67	73.7 GB	76.7 GB	—	Won't fit
Q6_K	6.56	85.3 GB	88.2 GB	—	Won't fit
Q8_0	8.50	110.5 GB	113.4 GB	—	Won't fit
F16	16.00	208 GB	210.9 GB	—	Won't fit

Want to set your own context length and KV-cache quantization? Use the interactive VRAM calculator.

购买此硬件 Apple MacBook Pro M5 Pro — 64 GB VRAM · 30 W board power 立即云端部署 RunPod 上的 NVIDIA A100 80GB — 低至 $1.39/小时 · 价格核实于 2026-07

或在 Vast.ai 比较，低至 $0.77/小时 (typical low · varies)

作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。

Recommended GPU

The cheapest catalogued GPU that runs Command R+ (104B) is the Apple M5 Pro (64 GB).

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。

Apple MacBook Pro M5 Pro

64 GB VRAM · 30 W board power

2026年价格波动较大——请以当前商品页价格为准。

在亚马逊查看价格

How to Run Command R+ (104B)

Install Ollama, then run:

ollama run command-r-plus

Weights on Hugging Face: CohereForAI/c4ai-command-r-plus.

Best for: enterprise rag, agent, complex retrieval.

Can I Run Command R+ (104B) on My GPU?

Other Command R Family Sizes

Command R (35B) — about 22 GB VRAM at Q4_K_M

Command R+ (104B) — Frequently Asked Questions

How much VRAM does Command R+ (104B) need?

About 64 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Command R+ (104B) run on an RTX 4090 (24 GB)?

No. Command R+ (104B) needs about 64 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.

How do I run Command R+ (104B) locally?

Install Ollama and run `ollama run command-r-plus`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Command R Family come in?

Command R (35B) (22 GB), Command R+ (104B) (64 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All Command R Family models | VRAM calculator | Check your own hardware