Skip to content
Updated minutes ago
NVIDIA

Alpamayo 1.5-10B

NVIDIA · dense · 10B parameters · 8,192 context

Quality
70.0

Parameters

10B

Context Window

8K tokens

Architecture

Dense

Best GPU

A100 40GB SXM

Intelligence Brief

Alpamayo 1.5-10B is a 10B parameter DENSE model from NVIDIA, featuring Grouped Query Attention (GQA) with 32 layers and 4,096 hidden dimensions. With a 8,192 token context window, it supports vision, reasoning. For self-hosted inference, A100 40GB SXM delivers optimal throughput at $807/month.

Architecture Details

TypeDENSE
Total Parameters10B
Active Parameters10B
Layers32
Hidden Dimension4,096
Attention Heads32
KV Heads8
Head Dimension128
Vocab Size128,256

Memory Requirements

BF16 Weights

20.0 GB

FP8 Weights

10.0 GB

INT4 Weights

5.0 GB

KV-Cache per Token131072 bytes
Activation Estimate1.00 GB

GPU Compatibility Matrix

Alpamayo 1.5-10B is compatible with 89% 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

A100 40GB SXMoptimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

419.8 tok/s

Latency (ITL)

2.4ms

Est. TTFT

0ms

Cost/Month

$807

Cost/M Tokens

$0.73

Use this config →
RTX 5090optimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

483.8 tok/s

Latency (ITL)

2.1ms

Est. TTFT

0ms

Cost/Month

$845

Cost/M Tokens

$0.66

Use this config →
A100 40GB PCIeoptimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

419.8 tok/s

Latency (ITL)

2.4ms

Est. TTFT

0ms

Cost/Month

$655

Cost/M Tokens

$0.59

Use this config →

Deployment Options

API

API Deployment

No API pricing available

Self-Hosted

Single GPU

A100 40GB SXM

$807/mo

Min VRAM: 10 GB

Scale

Multi-GPU

A4000 x2

194.0 tok/s

TP· $323/mo

API Pricing Comparison

No API pricing data available for this model.

Performance Estimates

Throughput by GPU

A100 40GB SXM
419.8 tok/s
RTX 5090
483.8 tok/s
A100 40GB PCIe
419.8 tok/s

VRAM Breakdown (A100 40GB SXM, BF16)

Weights
Act
Weights 20.0 GBKV-Cache 2.1 GBActivations 8.0 GBOverhead 1.6 GB

Precision Impact

bf16

20.0 GB

weights/GPU

~419.8 tok/s

fp8

10.0 GB

weights/GPU

int4

5.0 GB

weights/GPU

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllm

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Alpamayo 1.5-10B

Similar Models

Larger context, Lower qualityCompare →

GLM-4 9B

9.4B params · dense

Quality: 50

from $0.15/M

Larger context, Lower qualityCompare →
Larger context, Lower qualityCompare →

SOLAR 10.7B

10.7B params · dense

Quality: 50

from $0.30/M

Lower qualityCompare →

Gemma 2 9B

9.2B params · dense

Quality: 68

from $0.10/M

Similar specsCompare →

Frequently Asked Questions

How much VRAM does Alpamayo 1.5-10B need for inference?

Alpamayo 1.5-10B requires approximately 20.0 GB of VRAM at BF16 precision, 10.0 GB at FP8, or 5.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (131072 bytes per token) and activations (~1.00 GB).

What is the best GPU for Alpamayo 1.5-10B?

The top recommended GPU for Alpamayo 1.5-10B is the A100 40GB SXM using BF16 precision. It achieves approximately 419.8 tokens/sec at an estimated cost of $807/month ($0.73/M tokens). Score: 95/100.

How much does Alpamayo 1.5-10B inference cost?

Alpamayo 1.5-10B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.