Back to leaderboard

qwen2.5-0.5b-instruct

LM-STUDIO GGUF

qwen2 · 0.5B · Q4_K_M

Marginal

Mar 6, 2026 · Intel Core™ i5-5300U

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score
53 vs 82
Hardware Fit
89 vs 88
Quality Score
38 vs 80

Hardware

qwen2.5-0.5b-instr… unsloth-phi-4
MachineLENOVO 20BUS00700Mac mini
CPUIntel Core™ i5-5300UApple M4 Pro
Cores414
RAM16 GB64 GB
GPUIntel(R) HD Graphics 5500Apple M4 Pro
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2.5-0.5b-instr… unsloth-phi-4
Tokens/sec13.227.4
First chunk1339 ms457 ms
TTFT1.3 s457 ms
Load timeN/AN/A
Memory usage0.4 GB7.7 GB
Memory %2%12%

HW Fit Score Breakdown

qwen2.5-0.5b-instruct

Speed
41/50
TTFT
20/20
Memory
28/30

unsloth-phi-4

Speed
38/50
TTFT
20/20
Memory
30/30

Quality

qwen2.5-0.5b-instruct

Reasoning
5/20
Coding
4/20
Instruction
10/20
Structured
11/15
Math
3/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak

unsloth-phi-4

Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen2.5-0.5b-instr… details | View unsloth-phi-4 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