01.AI

Yi 1.5 34B

Name: Yi 1.5 34B
Rating: 60 (81 reviews)
Author: 01.AI

現行

HuggingFace

20.4Kダウンロード278いいねMay 2024公開日4K トークンコンテキストApache 2.0ライセンス32 基本品質

Yi 1.5 34B (34B parameters) requires approximately 26.2 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 31 GB of VRAM.

はじめに

— コピー&ペーストでローカル実行

Copy-paste commands to run Yi 1.5 34B on your machine.

Run

lms load Yi-1.5-34B-Chat && lms server start

Quick specs

Parameters34B

Architecturedense

Context4K tokens

Modalitytext

Min RAM13.3 GB

Rec. RAM20.7 GB (Q4_K_M)

LicenseApache 2.0

FamilyYi

✓ Chat✓ Reasoning

About this model

🐙 GitHub • 👾 Discord • 🐤 Twitter • 💬 WeChat

Yi 1.5 34Bのおすすめ

NVIDIA A100 40GBB

40 GB

RTX PRO 5000 Blackwell 48GBB

48 GB

MacBook Pro M4 Max 64GBB

このモデルを実行

Yi 1.5 34B on NVIDIA A100 40GB Yi 1.5 34B on RTX PRO 5000 Blackwell 48GB Yi 1.5 34B on MacBook Pro M4 Max 64GB

量子化オプション

量子化レベル別VRAM推定値

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.3 GB	Low	—
Q3_K_S	3	16.7 GB	Low	—
NVFP4	4	19.0 GB	Medium	—
Q4_K_M	4	20.7 GB	Medium	—
Q5_K_M	5	24.5 GB	High	—
Q6_K	6	27.9 GB	High	—
Q8_0	8	36.4 GB	Very High	—
F16	16	69.7 GB	Maximum	—

Quality benchmarks

Yi 1.5 34B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—

HumanEval+75.2%

Aider Polyglot—

LiveCodeBench—

Reasoning

MMLU-Pro39.1%

GPQA Diamond15.3%

MATH-50027.7%

ARC Challenge—

General

Chatbot Arena—

IFEval60.7%

Source: official · 2024-05-13

ハードウェア互換性

全ハードウェアの適合度推定

カリキュレーターを開く

Computing compatibility...

メモリ内訳

Reference: RTX 2060 6GB

Weights20.7 GB

KV Cache3.7 GB

Runtime1.2 GB

Headroom0.6 GB

よくある質問