Model Profile

DeepSeek-V2.5

Name: DeepSeek-V2.5
Author: deepseek-ai

4,096 ctxOpen weights

Use this page to decide where this model is a strong fit. Rankings below are benchmark-backed by use case, with explicit confidence and contributor metrics.

Identity

ID: deepseek-ai/DeepSeek-V2.5

Author: deepseek-ai

Origin: huggingface_catalog

Arch: unknown

Benchmark Coverage

Scored use cases: 8

Avg confidence: 13.3%

Evidence points: 30

Raw rows: 24

Weighted rows: 5

Catalog Metadata

Parameters: unknown

Context window: 4096

Downloads: 74,482

Some fit rows have limited benchmark evidence.

8 of 8 scored use cases have low confidence or thin contributor coverage.

Coverage Diagnostics

actively scored

Use-Case Scores

Total Measurements

Weighted Measurements

Weighted Sources

Raw Source Coverage

artificialanalysis_llm_performance 6eq_bench 5artificialanalysis_cost_quality_frontier 4artificialanalysis_judgemark_official 4artificialanalysis_deployment_perf 3aider_code_editing 2

Weighted Source Coverage

aider_code_editing 2eq_bench 2artificialanalysis_judgemark_official 1

Best Use Cases for This Model

Use Case	Vertical	Score	Confidence	Evidence	Top Contributor
Poetry and lyrics use_case.creative.poetry_lyrics	creative	10.8%	16.7%	4	Judgemark Official (EQ-Bench Slice): judgemark_score
Screenplay scene writing use_case.creative.screenplay_scene	creative	10.8%	16.7%	4	Judgemark Official (EQ-Bench Slice): judgemark_score
Ad copy variants use_case.mkt.ad_copy_variants	marketing_sales	9.5%	12.1%	3	EQ-Bench Leaderboard: eq_bench_score
Personalized sales outreach use_case.mkt.sales_outreach_personalized	marketing_sales	9.5%	12.1%	3	EQ-Bench Leaderboard: eq_bench_score
Long-form story co-author use_case.creative.longform_story	creative	9.1%	14.2%	4	Judgemark Official (EQ-Bench Slice): judgemark_score
Interactive fiction / DM use_case.creative.interactive_fiction_dm	creative	7.8%	12.2%	4	Judgemark Official (EQ-Bench Slice): judgemark_score
NPC dialogue use_case.gaming.npc_dialogue	creative	7.8%	12.2%	4	Judgemark Official (EQ-Bench Slice): judgemark_score
Lore bible generator use_case.creative.lore_bible	creative	6.7%	10.4%	4	Judgemark Official (EQ-Bench Slice): judgemark_score

Deployment Fit Calculator

Model

DeepSeek-V2.5

deepseek-ai/DeepSeek-V2.5

Hardware

Quantization: 4-bit

2-bit8-bit

Insufficient

Unknown parameter count. Cannot estimate deployment fit.

Required VRAM

~0.0GB

Est. Throughput

0.00 tok/s

Deployment Fit Matrix

GPU	4-bit	6-bit	8-bit
RTX 3060 12GB	Insufficient	Insufficient	Insufficient
RTX 3090 24GB	Insufficient	Insufficient	Insufficient
RTX 4090 24GB	Insufficient	Insufficient	Insufficient
Mac Studio M2 Ultra 192GB	Insufficient	Insufficient	Insufficient