Skip to content
Updated minutes ago
Cohere

Command R (August 2024)

Cohere · dense · 35B parameters · 128,000 context

Quality
68.0

Parameters

35B

Context Window

125K tokens

Architecture

Dense

Best GPU

H20

Cheapest API

$0.60/M

Quality Score

68/100

Intelligence Brief

Command R (August 2024) is a 35B parameter DENSE model from Cohere, featuring Grouped Query Attention (GQA) with 40 layers and 8,192 hidden dimensions. With a 128,000 token context window, it supports tools, structured output, code, math, multilingual. On standardized benchmarks, it achieves MMLU 73, HumanEval 42, GSM8K 75. The most cost-effective API deployment is via cohere at $0.60/M output tokens. For self-hosted inference, H20 delivers optimal throughput at $940/month.

Architecture Details

TypeDENSE
Total Parameters35B
Active Parameters35B
Layers40
Hidden Dimension8,192
Attention Heads64
KV Heads8
Head Dimension128
Vocab Size256,000

Memory Requirements

BF16 Weights

70.0 GB

FP8 Weights

35.0 GB

INT4 Weights

17.5 GB

KV-Cache per Token327680 bytes
Activation Estimate2.00 GB

GPU Compatibility Matrix

Command R (August 2024) is compatible with 57% of GPU configurations across 41 GPUs at 3 precision levels.

BF16 (Full)
FP8 (Half)
INT4 (Quarter)
Blackwell(7 GPUs)
B200 NVL (pair)360GB
B300288GB
B100 SXM192GB
GB200 NVL72 (per GPU)192GB
Hopper(7 GPUs)
H100 NVL 94GB (per GPU pair)188GB
H200 SXM141GB
H2096GB
GH20096GB
Ada Lovelace(11 GPUs)
L40S48GB
L4048GB
RTX 6000 Ada48GB
L2048GB
Ampere(16 GPUs)
A100 80GB SXM80GB
A100 80GB PCIe80GB
A1664GB
RTX A600048GB
Legend:No fitVery tightTightModerateGoodExcellent

GPU Recommendations

H20optimal

FP8 · 1 GPU · tensorrt-llm

100/100

score

Throughput

956.1 tok/s

Latency (ITL)

1.0ms

Est. TTFT

0ms

Cost/Month

$940

Cost/M Tokens

$0.37

Use this config →
B200 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

98/100

score

Throughput

1.1K tok/s

Latency (ITL)

1.0ms

Est. TTFT

0ms

Cost/Month

$4261

Cost/M Tokens

$1.54

Use this config →
H200 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

95/100

score

Throughput

1.1K tok/s

Latency (ITL)

1.0ms

Est. TTFT

0ms

Cost/Month

$2553

Cost/M Tokens

$0.93

Use this config →

Deployment Options

API

API Deployment

cohere

$0.60/M

output tokens

Self-Hosted

Single GPU

H20

$940/mo

Min VRAM: 35 GB

Scale

Multi-GPU

RTX A6000 x2

104.7 tok/s

TP· $930/mo

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
cohere$0.15$0.60
Cheapest

Cost Analysis

ProviderInput $/MOutput $/M~Monthly Cost
cohereBest Value$0.15$0.60$4

Cost per 1,000 Requests

Short (500 tok)

$0.20

via cohere

Medium (2K tok)

$0.78

via cohere

Long (8K tok)

$2.40

via cohere

Performance Estimates

Throughput by GPU

H20
956.1 tok/s
B200 SXM
1.1K tok/s
H200 SXM
1.1K tok/s

VRAM Breakdown (H20, FP8)

Weights
Act
Weights 35.0 GBKV-Cache 1.3 GBActivations 16.0 GBOverhead 1.8 GB

Precision Impact

bf16

70.0 GB

weights/GPU

fp8

35.0 GB

weights/GPU

~956.1 tok/s

int4

17.5 GB

weights/GPU

Quality Benchmarks

Average
71th percentile across all models
MMLU
73.0
Below Average (41th pctile)
HumanEval
42.0
Below Average (30th pctile)
GSM8K
75.0
Below Average (36th pctile)
MT-Bench
78.0
Bottom 25% (0th pctile)

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgi

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Command R (August 2024)

Similar Models

Command R

35B params · dense

Quality: 68

from $0.50/M

Similar specsCompare →

Command R+

104B params · dense

Quality: 68

from $2.00/M

More expensive, Larger modelCompare →

Aya 23 35B

35B params · dense

Quality: 50

from $1.50/M

Lower quality, More expensiveCompare →

Yi 1.5 34B

34.4B params · dense

Quality: 72

from $0.80/M

Larger contextCompare →

Code Llama 34B

34B params · dense

Quality: 55

from $0.78/M

Lower qualityCompare →

Frequently Asked Questions

How much VRAM does Command R (August 2024) need for inference?

Command R (August 2024) requires approximately 70.0 GB of VRAM at BF16 precision, 35.0 GB at FP8, or 17.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (327680 bytes per token) and activations (~2.00 GB).

What is the best GPU for Command R (August 2024)?

The top recommended GPU for Command R (August 2024) is the H20 using FP8 precision. It achieves approximately 956.1 tokens/sec at an estimated cost of $940/month ($0.37/M tokens). Score: 100/100.

How much does Command R (August 2024) inference cost?

Command R (August 2024) API inference starts from $0.15/M input tokens and $0.60/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.