Model

Yi-6B

OPEN

01.AI · Yi family · released Nov 2, 2023

Smaller bilingual EN/ZH sibling of Yi-34B from 01.AI's debut Yi series, trained on 3.1T tokens under Apache 2.0.

ReasoningCodingVisionFunction callingTool useAgentic

42.9

Elo · rank #397

Parameters

Active params

6B (dense)

Context

4K tokens

Architecture

Dense decoder-only transformer (Llama-style, GQA, SwiGLU, RoPE with adjusted base frequency)

License

Apache 2.0

Languages

API price (in/out)

No hosted API

Modalities

text

Benchmark results

Bar shows position within the tracked field; marker = field best

ARC-ChallengeReasoning50.3%#124

best: Llama 3.1 405B · 96.9%

BIG-Bench HardReasoning42.8%#109

best: ERNIE 4.5 300B-A47B · 94.3%

C-EvalKnowledge72.0%#40

best: Qwen3.6-Plus · 93.3%

CMMLUKnowledge75.5%#16

best: Doubao-1.5-Pro · 90.9%

GSM8KMath32.5%#150

best: Llama 3.1 405B · 96.8%

HellaSwagReasoning74.4%#114

best: Claude 3 Opus · 95.4%

HumanEvalCoding15.9%#174

best: Claude Opus 4.5 · 99.4%

MATH-500Math4.6%#197

best: GPT-5 · 99.4%

MBPPCoding26.3%#101

best: Llama-3.3-Nemotron-Super-49B v1 (Reasoning On) · 91.3%

MMLUKnowledge63.2%#189

best: OpenAI o3 · 92.9%

TruthfulQAKnowledge41.9%#72

best: Phi-3.5-MoE (16x3.8B, 6.6B active) · 77.5%

WinoGrandeReasoning71.3%#92

best: PaLM 2 · 90.9%

Run it locally

VRAM @ Q4

4.5 GB

VRAM @ FP16

12.1 GB

Fits on (Q4)

RTX 3060 12GBRTX 4070 Ti 16GBRTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB

Throughput data unavailable.

Quantizations

GGUF Q4_K_M · AWQ · GPTQ

Yi family

Elo progression across releases

Yi-34BNov 2023451.7 Yi-6BNov 202342.9

Resources

HF01-ai/Yi-6B GH01-ai/Yi APIAvailable via 01.AI API

API price weights · each benchmark row carries its own source badge (see methodology)