Alibaba

Qwen 2.5 Math 7B

Name: Qwen 2.5 Math 7B
Rating: 53 (193 reviews)
Author: Alibaba

現行

HuggingFace

60.5Kダウンロード90いいねSep 2024公開日4K トークンコンテキストApache 2.0ライセンス14 入門品質

Qwen 2.5 Math 7B (7B parameters) requires approximately 6.6 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 8 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 Qwen 2.5 Math 7B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "Qwen/Qwen2.5-Math-7B-Instruct" \
  --hf-file "Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Quick specs

Parameters7B

Architecturedense

Context4K tokens

Modalitytext

Min RAM2.7 GB

Rec. RAM4.3 GB (Q4_K_M)

LicenseApache 2.0

FamilyQwen

✓ Reasoning

About this model

> [!Warning] > > > 🚨 Qwen2.5-Math mainly supports solving English and Chinese math problems through CoT and TIR. We do not recommend using this series of models for other tasks. > >

Qwen 2.5 Math 7Bのおすすめ

このモデルを実行

Qwen 2.5 Math 7B on RTX 3080 10GB Qwen 2.5 Math 7B on RTX 2080 Ti 11GB Qwen 2.5 Math 7B on GTX 1080 Ti 11GB

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	2.7 GB	Low	—
Q3_K_S	3	3.4 GB	Low	—
NVFP4	4	3.9 GB	Medium	—
Q4_K_M	4	4.3 GB	Medium	—
Q5_K_M	5	5.0 GB	High	—
Q6_K	6	5.7 GB	High	—
Q8_0	8	7.5 GB	Very High	—
F16	16	14.3 GB	Maximum	—

Quality benchmarks

Qwen 2.5 Math 7B benchmark scores

Benchmark verified

Reasoning

MMLU-Pro20.2%

GPQA Diamond1.6%

MATH-50058.1%

ARC Challenge—

General

Chatbot Arena—

IFEval26.4%

Source: community · 2025-01-01

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

Weights4.3 GB

KV Cache0.9 GB

Runtime0.9 GB

Headroom0.6 GB

よくある質問