BestLLMfor EN Your hardware. Your LLM. Your call.
APIOpen data Find my LLM
Model fiche

Qwen 2.5 Coder 7B

By Alibaba · China

code
Parameters
7B
License
Apache 2.0
Context
128k
VRAM (Q4)
5 GB
Released
November 2024

Overview

A 7B coding specialist from Alibaba covering 92 programming languages with a 128k context. Competitive with proprietary models on HumanEval at this size.

When to pick this model

  • Local IDE autocomplete and inline code suggestions
  • Code review and refactoring assistants on a consumer GPU
  • Multi-language codebases needing broad language coverage
  • Repo-scale Q&A using the 128k window
  • Cheap, high-throughput code generation pipelines

VRAM requirements by quantization

QuantizationVRAM required
Q4_K_M (recommended)5 GB
Q5_K_M6 GB
Q8_09 GB
FP16 (no quantization)16 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Published benchmark scores

BenchmarkScore
HumanEval88.4
MBPP83.5

Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.

Strengths

  • Strong HumanEval and code completion for a 7B
  • 128k context for repo-scale prompts
  • Coverage of 92 programming languages
  • Apache 2.0 license

Limitations

  • Beaten clearly by the 32B variant on complex code tasks
  • Weaker than general 7Bs for non-coding chat
  • Limited reasoning on multi-step debugging

Architecture & training

Architecture: Dense Transformer specialized for code · Qwen 2.5 Coder 7B

Training: Qwen 2.5 pre-training + 5.5T code tokens, 92 programming languages.

Verdict

The right pick when you want a local code model that fits on a single 8GB-class GPU and still pulls its weight.

Quick start

ollama run qwen2.5-coder:7b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.

Tools

Is Qwen 2.5 Coder 7B the right pick for you?

Compute self-hosted ROI → Back to catalog