Model Profile

Phi-3-medium-128k-instruct

Name: Phi-3-medium-128k-instruct
Author: microsoft

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: microsoft/Phi-3-medium-128k-instruct

Author: microsoft

Origin: huggingface_catalog

Arch: unknown

Benchmark Coverage

Scored use cases: 9

Avg confidence: 14.7%

Evidence points: 27

Raw rows: 86

Weighted rows: 4

Catalog Metadata

Parameters: unknown

Context window: 4096

Downloads: 52,521

Some fit rows have limited benchmark evidence.

9 of 9 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

repoqa_leaderboard 74duckdb_nsql_leaderboard 12

Weighted Source Coverage

duckdb_nsql_leaderboard 2repoqa_leaderboard 2

Best Use Cases for This Model

Use Case	Vertical	Score	Confidence	Evidence	Top Contributor
Debugging assistant use_case.dev.debugging	developer_tools	11.4%	15.6%	3	RepoQA Official Results: overall_average_pass_at_1_pct
Metric definition workshop use_case.data.metric_definition_workshop	data_analytics	10.5%	19.2%	3	DuckDB NSQL Leaderboard: all_execution_accuracy
Unit test generation use_case.dev.test_generation	developer_tools	9.7%	13.3%	3	RepoQA Official Results: overall_average_pass_at_1_pct
SQL debugging use_case.data.sql_debugging	data_analytics	9.5%	17.7%	3	DuckDB NSQL Leaderboard: all_execution_accuracy
Data quality assistant use_case.data.data_quality_assistant	data_analytics	8.3%	15.0%	3	DuckDB NSQL Leaderboard: all_execution_accuracy
Refactoring assistant use_case.dev.refactoring	developer_tools	7.8%	10.7%	3	RepoQA Official Results: overall_average_pass_at_1_pct
Text-to-SQL analyst assistant use_case.data.text_to_sql	data_analytics	7.7%	14.4%	3	DuckDB NSQL Leaderboard: all_execution_accuracy
Executive brief from metrics use_case.data.exec_brief_from_metrics	data_analytics	7.4%	13.5%	3	DuckDB NSQL Leaderboard: all_execution_accuracy
Insight mining from text corpora use_case.data.insight_mining	data_analytics	7.2%	13.0%	3	DuckDB NSQL Leaderboard: all_execution_accuracy

Deployment Fit Calculator

Model

Phi-3-medium-128k-instruct

microsoft/Phi-3-medium-128k-instruct

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