Back to leaderboard

qwen2.5-0.5b-instruct-mlx

LM-STUDIO MLX

qwen2 · 0.5B · 4bit

Marginal

Mar 4, 2026 · Apple M4

granite-3.1-1b-a400m-instruct

LM-STUDIO GGUF

granitemoe · 1B · Q4_K_M

Marginal

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score
52 vs 50
Hardware Fit
100 vs 95
Quality Score
31 vs 31

Hardware

qwen2.5-0.5b-instr… granite-3.1-1b-a40…
MachineMacBook AirLENOVO 20BUS00700
CPUApple M4Intel Core™ i5-5300U
Cores104
RAM32 GB16 GB
GPUApple M4Intel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen2.5-0.5b-instr… granite-3.1-1b-a40…
Tokens/sec257.519.6
First chunk99 ms1141 ms
TTFT99 ms1.1 s
Load timeN/AN/A
Memory usage0.3 GB0.8 GB
Memory %1%5%

HW Fit Score Breakdown

qwen2.5-0.5b-instruct-mlx

Speed
50/50
TTFT
20/20
Memory
30/30

granite-3.1-1b-a400m-in…

Speed
50/50
TTFT
20/20
Memory
25/30

Quality

qwen2.5-0.5b-instruct-mlx

Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak

granite-3.1-1b-a400m-in…

Reasoning
3/20
Coding
3/20
Instruction
7/20
Structured
10/15
Math
2/15
Multilingual
6/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Poor Multilingual: Adequate
View qwen2.5-0.5b-instr… details | View granite-3.1-1b-a40… details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest