Updated minutes ago
Yandex

YaLM 100B

Yandex · dense · 100B parameters · 2,048 context

Quality
50.0
Calculate ROI →Compare with othersFine-Tune This Model →

Parameters

100B

Context Window

2K tokens

Architecture

Dense

Best GPU

B200 SXM

Intelligence Brief

YaLM 100B is a 100B parameter DENSE model from Yandex, featuring Multi-Head Attention (MHA) with 80 layers and 10,240 hidden dimensions. With a 2,048 token context window, it supports multilingual. For self-hosted inference, B200 SXM delivers optimal throughput at $4261/month.

Architecture Details

TypeDENSE
Total Parameters100B
Active Parameters100B
Layers80
Hidden Dimension10,240
Attention Heads80
KV Heads80
Head Dimension128
Vocab Size128,000

Memory Requirements

BF16 Weights

200.0 GB

FP8 Weights

100.0 GB

INT4 Weights

50.0 GB

KV-Cache per Token3276800 bytes
Activation Estimate3.50 GB

Fits on (single GPU) — most practical first

BEST FITInstinct MI21064GBINT4A1664GBINT4H100 SXM80GBINT4H100 PCIe80GBINT4A100 80GB SXM80GBINT4A100 80GB PCIe80GBINT4H100 NVL94GBINT4H2096GBINT4Gaudi 296GBINT4GH20096GBINT4Trainium296GBINT4Instinct MI250X128GBFP8

GPU Compatibility Matrix

YaLM 100B is compatible with 21% of GPU configurations across 41 GPUs at 3 precision levels.

BF16 (Full)
FP8 (Half)
INT4 (Quarter)
Blackwell(7 GPUs)
B200 NVL (pair)360GB
44%
72%
86%
B300288GB
31%
65%
83%
B100 SXM192GB
✗
48%
74%
GB200 NVL72 (per GPU)192GB
✗
48%
74%
Hopper(7 GPUs)
H100 NVL 94GB (per GPU pair)188GB
✗
47%
73%
H200 SXM141GB
✗
29%
65%
H2096GB
✗
✗
48%
GH20096GB
✗
✗
48%
Ada Lovelace(11 GPUs)
L40S48GB
✗
✗
✗
L4048GB
✗
✗
✗
RTX 6000 Ada48GB
✗
✗
✗
L2048GB
✗
✗
✗
Ampere(16 GPUs)
A100 80GB SXM80GB
✗
✗
38%
A100 80GB PCIe80GB
✗
✗
38%
A1664GB
✗
✗
22%
RTX A600048GB
✗
✗
✗
Legend:No fitVery tightTightModerateGoodExcellent

GPU Recommendations

B200 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

100/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$4261

Cost/M Tokens

$5.79

Use this config →
B100 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

100/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$4271

Cost/M Tokens

$5.80

Use this config →
GB200 NVL72 (per GPU)optimal

FP8 · 1 GPU · tensorrt-llm

100/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$6169

Cost/M Tokens

$8.38

Use this config →

Deployment Options

API

API Deployment

No API pricing available

Self-Hosted

Single GPU

B200 SXM

$4261/mo

Min VRAM: 100 GB

Scale

Multi-GPU

H100 SXM x2

280.0 tok/s

TP· $3587/mo

Open Full Calculator →

API Pricing Comparison

No API pricing data available for this model.

Performance Estimates

Throughput by GPU

B200 SXM
280.0 tok/s
B100 SXM
280.0 tok/s
GB200 NVL72 (per GPU)
280.0 tok/s

VRAM Breakdown (B200 SXM, FP8)

Weights
KV
Act
Weights 100.0 GBKV-Cache 26.8 GBActivations 28.0 GBOverhead 5.0 GB

Precision Impact

bf16

200.0 GB

weights/GPU

fp8

100.0 GB

weights/GPU

~280.0 tok/s

int4

50.0 GB

weights/GPU

Capabilities

Features

✗ Tool Use✗ Vision✗ Code✗ Math✗ Reasoning✓ Multilingual✗ Structured Output

Supported Frameworks

vllmtgi

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy YaLM 100B

Similar Models

Inflection 3

100B params · dense

Quality: 74

from $15.00/M

Larger context, Higher qualityCompare →

Yi-Large

102.6B params · moe

Quality: 74

from $3.00/M

Larger context, Higher qualityCompare →

Command R+

104B params · dense

Quality: 68

from $2.00/M

Larger context, Higher qualityCompare →

Llama 4 Scout

109B params · moe

Quality: 73

from $0.30/M

Larger context, Higher qualityCompare →

Llama 3.2 90B Vision

90B params · dense

Quality: 84

from $0.90/M

Larger context, Higher qualityCompare →

Frequently Asked Questions

How much VRAM does YaLM 100B need for inference?

YaLM 100B requires approximately 200.0 GB of VRAM at BF16 precision, 100.0 GB at FP8, or 50.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (3276800 bytes per token) and activations (~3.50 GB).

What is the best GPU for YaLM 100B?

The top recommended GPU for YaLM 100B is the B200 SXM using FP8 precision. It achieves approximately 280.0 tokens/sec at an estimated cost of $4261/month ($5.79/M tokens). Score: 100/100.

How much does YaLM 100B inference cost?

YaLM 100B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.