qwen2.5-coder-7b-instruct-mlx

qwen2 · 7B · 4bit

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 3, 2026 · Submitted by Topaz750

Top 12% Compare

Global Score

79 /100

Good

Hardware Fit

92/100

Quality

73/100

Get this model

🦙

Ollama

ollama pull qwen2.5-coder-7b-instruct-mlx

View on Ollama Library

ollama.com/library/qwen2.5-coder-7b-instruct-mlx

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: MacBook Air
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 22.5
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.7
First chunk latency Delay before the first streamed chunk arrives from runtime: 529 ms
Time to first token How fast the model starts responding — lower is better: 529 ms
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 4.0 GB (13%)
Total tokens Total number of tokens generated across all benchmark prompts: 964

Score breakdown

Speed

44/50

Time to first token

20/20

Memory

28/30

Quality

Reasoning

10/20

Coding

18/20

Instruction following

14/20

Structured output

13/15

Math

9/15

Multilingual

9/10

Category levels

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

Metadata

Spec version: 0.2.0
Runtime: LM Studio 0.4.6+1
Model format: MLX
Hardware profile: BALANCED
Result hash: c3c24758c3702e493bb4fffe7cb53c989229502e489c77c33108cabb4965d74f

Interpretation

Hardware fit: 92/100. Overall suitability: GOOD (Global 79/100). Category profile: Reasoning: Adequate, Coding: Strong, Instruction Following: Adequate, Structured Output: Strong, Math: Adequate, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running