How much VRAM does Command R 35B need?

Command R 35B requires approximately 0.0 GB VRAM at Q4_K_M quantization with 1K context and 10% overhead. At Q8_0 it needs ~0.0 GB, and at FP16 ~0.0 GB. Use the PCPARTGUIDE VRAM Calculator for exact requirements at any context length and overhead setting.

Can I run Command R 35B on a consumer GPU?

Yes, Command R 35B can run on consumer GPUs. At Q4_K_M quantization with moderate context length, it fits on a 24 GB GPU. For best performance, use a 24 GB or larger GPU with at least 8 GB VRAM for reasonable context lengths.

What is Command R 35B's context window?

Command R 35B supports a maximum context window of 131,072 tokens. The default context is 8,192 tokens. Larger contexts require proportionally more VRAM for the KV cache — use the VRAM Calculator to estimate exact requirements at your target context length.

What quantization level should I use for Command R 35B?

For Command R 35B, start with Q4_K_M (~0.0 GB) if VRAM-limited. Q8_0 offers better quality at ~2× the VRAM. If you have enough VRAM, Q6_K (~1.5× Q4 VRAM) provides a good balance. For models this large, Q3_K_M may be necessary to fit on consumer hardware.

How does Command R 35B compare to similar models?

Command R 35B is a 35.0B Dense model from the Cohere family. Browse other Cohere models on the PCPARTGUIDE directory for comparable alternatives with different parameter counts and VRAM requirements. Use the Model Transparency scores to assess documentation quality and reproducibility.

CohereDenseCC-BY-NC 4.0

Command R 35B

35.0B

Parameters

128K

Max Context

Dense

Architecture

Mar 11, 2024

Released

Text

Modality

About Command R 35B

Command R 35B is Cohere's RAG-optimized model, purpose-built for retrieval-augmented generation, multilingual enterprise tasks, and tool use. At 35B parameters with 128K context and strong performance across 10 languages, it excels at grounded generation — citing sources, following structured instructions, and calling external tools. The CC-BY-NC license limits commercial use without Cohere's permission. At Q4_K_M it needs ~20 GB VRAM, fitting on 24 GB GPUs. Still relevant for enterprise RAG workflows where tool use and grounded generation are priorities.

RAGEnterpriseTool UseMultilingual

Technical Specifications

Total Parameters35.0B

ArchitectureDense

Attention TypeGQA (Grouped Query Attention)

Hidden Dimensiond = 8,192

Transformer Layers40

Attention Heads64

KV Headsn_kv = 8

Head Dimensiond_head = 128

Activation FunctionSwiGLU

NormalizationRMSNorm

Position EmbeddingRoPE

System Requirements

Estimated VRAM at 10% overhead for different quantization methods and context sizes.

Quantization	1K ctx	128K ctx
Q4_K_M0.50 B/W ~97% of FP16	18.25Consumer GPU	38.09Datacenter GPU
Q8_01.00 B/W ~100% of FP16	36.34Datacenter GPU	56.18Datacenter GPU
F162.00 B/W Reference	72.52Datacenter GPU	92.36Cluster / Multi-GPU

Fits 24 GB consumer GPU

Fits 80 GB datacenter GPU

Requires cluster / multi-GPU

Other Cohere Models

View All

Command R+ 104B

Params

104.0B

Layers

Context

125K

Find the right GPU for Command R 35B

Use the interactive VRAM Calculator to see exactly how much memory you need at any quantization level, context length, and overhead setting.

Open VRAM Calculator Best GPU Guide VRAM Guide