Skip to content
Updated minutes ago
01.AI

Yi Coder 9B

01.AI · dense · 8.8B parameters · 131,072 context

Quality
50.0

Parameters

8.8B

Context Window

128K tokens

Architecture

Dense

Best GPU

A30

Intelligence Brief

Yi Coder 9B is a 8.8B parameter DENSE model from 01.AI, featuring Grouped Query Attention (GQA) with 48 layers and 3,584 hidden dimensions. With a 131,072 token context window, it supports structured output, code, math, multilingual. For self-hosted inference, A30 delivers optimal throughput at $332/month.

Architecture Details

TypeDENSE
Total Parameters8.8B
Active Parameters8.8B
Layers48
Hidden Dimension3,584
Attention Heads28
KV Heads4
Head Dimension128
Vocab Size64,000

Memory Requirements

BF16 Weights

17.6 GB

FP8 Weights

8.8 GB

INT4 Weights

4.4 GB

KV-Cache per Token98304 bytes
Activation Estimate1.00 GB

GPU Compatibility Matrix

Yi Coder 9B is compatible with 90% 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

A30optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

286.2 tok/s

Latency (ITL)

3.5ms

Est. TTFT

1ms

Cost/Month

$332

Cost/M Tokens

$0.44

Use this config →
RTX 4090optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

309.3 tok/s

Latency (ITL)

3.2ms

Est. TTFT

1ms

Cost/Month

$370

Cost/M Tokens

$0.46

Use this config →
RTX 3090optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

287.2 tok/s

Latency (ITL)

3.5ms

Est. TTFT

1ms

Cost/Month

$180

Cost/M Tokens

$0.24

Use this config →

Deployment Options

API

API Deployment

No API pricing available

Self-Hosted

Single GPU

A30

$332/mo

Min VRAM: 9 GB

Scale

Multi-GPU

RTX 3060 x2

174.8 tok/s

TP· $114/mo

API Pricing Comparison

No API pricing data available for this model.

Performance Estimates

Throughput by GPU

A30
286.2 tok/s
RTX 4090
309.3 tok/s
RTX 3090
287.2 tok/s

VRAM Breakdown (A30, BF16)

Weights
Act
Weights 17.6 GBKV-Cache 1.6 GBActivations 8.0 GBOverhead 1.4 GB

Precision Impact

bf16

17.6 GB

weights/GPU

~286.2 tok/s

fp8

8.8 GB

weights/GPU

int4

4.4 GB

weights/GPU

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgitensorrt-llmollama

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Yi Coder 9B

Similar Models

Yi 1.5 9B

8.83B params · dense

Quality: 62

from $0.20/M

Smaller context, Higher qualityCompare →
Smaller context, Higher qualityCompare →

Gemma 2 9B

9.2B params · dense

Quality: 68

from $0.10/M

Smaller context, Higher qualityCompare →

GLM-4 9B

9.4B params · dense

Quality: 50

from $0.15/M

Similar specsCompare →

Frequently Asked Questions

How much VRAM does Yi Coder 9B need for inference?

Yi Coder 9B requires approximately 17.6 GB of VRAM at BF16 precision, 8.8 GB at FP8, or 4.4 GB at INT4 quantization. Additional VRAM is needed for KV-cache (98304 bytes per token) and activations (~1.00 GB).

What is the best GPU for Yi Coder 9B?

The top recommended GPU for Yi Coder 9B is the A30 using BF16 precision. It achieves approximately 286.2 tokens/sec at an estimated cost of $332/month ($0.44/M tokens). Score: 100/100.

How much does Yi Coder 9B inference cost?

Yi Coder 9B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.