Will It Run AI

AlibabaAlibaba

Qwen 2.5 14B

Aktuell
huggingfaceHuggingFaceollamaOllama
2.1MDownloads342LikesSep 2024Veröffentlicht131K TokenKontextApache 2.0Lizenz73 StarkQualität

Qwen 2.5 14B (14B parameters) requires approximately 13.3 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 16 GB of VRAM.

Loslegen

— kopieren & einfügen, um lokal auszuführen

Copy-paste commands to run Qwen 2.5 14B on your machine.

Run

ollama run qwen2.5

Quick specs

Parameters14B
Architecturedense
Context131K tokens
Modalitytext
Min RAM5.5 GB
Rec. RAM8.5 GB (Q4_K_M)
LicenseApache 2.0
FamilyQwen
✓ Chat✓ Reasoning

About this model

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:

  • •Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models...
  • •Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g,...
  • •Long-context Support: up to 128K tokens and can generate up to 8K tokens
  • •Multilingual support: for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean,...

Verwandte Modelle

Deine Hardware

Erkennung...

Schnellauswahl

Bestes BudgetA
RX 7600 XT 16GB~$329 — 21 tok/s
NVIDIA
Beste GesamtwahlS
RTX A4500 20GB~$2,000 — 63 tok/s

Beste Hardware

Top-Empfehlungen für Qwen 2.5 14B

NVIDIA
RTX A4500 20GBS
20 GB
RX 7900 XT 20GBS
20 GB
NVIDIA
RTX 4090 24GBS
24 GB
NVIDIA
NVIDIA A30 24GBS
24 GB
NVIDIA
RTX 5090 Laptop 24GBS
24 GB

Dieses Modell ausführen

Qwen 2.5 14B on RTX A4500 20GBQwen 2.5 14B on RX 7900 XT 20GBQwen 2.5 14B on RTX 4090 24GB

Quantisierungsoptionen

VRAM-Schätzungen nach Quantisierungsstufe

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
5.5 GB
Low—
Q3_K_S
3
6.9 GB
Low—
NVFP4
4
7.8 GB
Medium—
Q4_K_M
4
8.5 GB
Medium—
Q5_K_M
5
10.1 GB
High—
Q6_K
6
11.5 GB
High—
Q8_0
8
15.0 GB
Very High—
F16
16
28.7 GB
Maximum—

Quality benchmarks

Qwen 2.5 14B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—
HumanEval+83.5%
Aider Polyglot—
LiveCodeBench42.6%

Reasoning

MMLU-Pro63.7%
GPQA Diamond45.5%
MATH-50080.0%
ARC Challenge—

General

Chatbot Arena—
IFEval81.0%

Source: official · 2024-09-19

Hardware-Kompatibilität

Eignungsschätzungen für alle Hardware

Rechner öffnen

Computing compatibility...

Speicheraufschlüsselung

Reference: RTX 2060 6GB

Weights8.5 GB
KV Cache2.9 GB
Runtime1.2 GB
Headroom0.6 GB

Häufig gestellte Fragen

FAQ — Qwen 2.5 14B

Siehe auch

QuantisierungsleitfadenBewertungsmethodikRechner öffnen