How much VRAM does Command R 35B need?

About 22.9 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 27.7 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.

Will Command R 35B run on a 32GB GPU?

Yes — at Q4_K_M and 4K context it needs about 22.9 GB, which leaves 9.1 GB spare on a RTX 5090, or on any of the other 32 GB cards here (4 in all). That is the smallest size in this index that clears it comfortably; 26 of 78 do.

Which quantization of Command R 35B should I use?

Q4_K_M has the lowest published quality loss (3.0%), and Q4_K_M is the level most people run. All 2 levels in the index are Q4_K_M, GPTQ INT4.

Command R 35B

35B

Cohere

⚠ Superseded · Prefer Qwen3.8 27B

This index would suggest Qwen3.8 27B instead today — longer context (128K → 256K tokens). The numbers below are still accurate; they are just for a model you probably should not start with. Compare the two →

Cohere's RAG-optimised model. Excellent retrieval-augmented generation. Sizes here assume grouped-query attention with 8 KV heads (about 5 GB of cache at 32K). The original March 2024 release (c4ai-command-r-v01) keeps a full cache for all 64 heads — about 40 GB at 32K — so check which build you download before planning long context.

Pro GPU

131K

Max Context

Quant Variants

GGUF Q4_K_M

Best Quality

97.0%

Accuracy Retained

Calculate VRAM Hugging Face Compare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports

Format	Level	BPW	VRAM	PPL Loss	Speed	Source	Actions
GGUF	Q4_K_M	4.85	22.8 GB	3.0%	42 tok/s	Estimated	Calc HF
GPTQ	INT4	4	20.5 GB	4.5%	55 tok/s	Estimated	Calc HF

Similar models

Compare with Qwen2.5 32B

32B

Qwen2.5 32B Instruct

Alibaba Qwen2.5

Consumer GPUPro GPU

16.4 GBmin VRAM97.3%accuracy

Near-GPT-4 reasoning on a 24GB VRAM card (Q4_K_S). Groundbreaking value.

24B

Mistral Small 24B Instruct

Mistral AI

Consumer GPUPro GPU

13.5 GBmin VRAM97.8%accuracy

Mistral's efficient 24B. Strong multilingual; fits on 24GB with Q4.

34B

Yi 1.5 34B Chat

01.AI Yi

Consumer GPUPro GPU

19.8 GBmin VRAM97.2%accuracy

01.AI's strong bilingual (EN/ZH) model. Competitive with Qwen 32B.

27B

Gemma 2 27B Instruct

Google Gemma 2

Consumer GPUPro GPU

16.2 GBmin VRAM98.7%accuracy

Largest open Gemma 2. Strong reasoning; needs 24GB+ VRAM at Q4.

Running Command R 35B locally

At Q4_K_M and 4K of context, Command R 35B needs about 22.9 GB — 20.2 GB of weights, 0.63 GB of KV cache and a 2.1 GB activation buffer. The smallest cards in this index that clear that comfortably are 32 GB ones — 4 of them, from the RTX 5090 up — and 26 of the 78 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 4.37 GB, taking the total to 27.7 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 128K; holding all of it at Q4_K_M would need about 44 GB.

Which build to download

This index tracks 2 formats for it — GGUF, GPTQ — across 2 levels. Q4_K_M carries the lowest published perplexity loss at 3.0%. The fastest level listed is GPTQ INT4 at about 55 tok/s on an RTX 4090, batch 1 — an estimate, not a run on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving.

Common questions

How much VRAM does Command R 35B need?: About 22.9 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 27.7 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
Will Command R 35B run on a 32GB GPU?: Yes — at Q4_K_M and 4K context it needs about 22.9 GB, which leaves 9.1 GB spare on a RTX 5090, or on any of the other 32 GB cards here (4 in all). That is the smallest size in this index that clears it comfortably; 26 of 78 do.
Which quantization of Command R 35B should I use?: Q4_K_M has the lowest published quality loss (3.0%), and Q4_K_M is the level most people run. All 2 levels in the index are Q4_K_M, GPTQ INT4.

Where this model fits

Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.

Runs comfortably on: RTX 509032GB · +9.1 Arc Pro B70 32G32GB · +9.1 Radeon AI PRO R9700 32G32GB · +9.1 Instinct MI100 32G32GB · +9.1 Mac M3 Pro 36G36GB · +4.1
Tight but possible: RTX 309024GB Radeon RX 7900 XTX24GB RTX 409024GB
Just misses: Radeon RX 7900 XT+2.9GB over Mac M4 24G+4.9GB over
Ships in: GGUF GPTQ
Compared here: GGUF vs GPTQ
Try it yourself: Size it in the calculator Generate the run command

How to actually run this

Deployment guides for this model and this class of hardware.

This page's figures change when the model or the runtime does.Last updated 2026-10-20 RSS → /feed.xml