Back to leaderboard

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

qwen2.5-0.5b-instruct

LM-STUDIO GGUF

qwen2 · 0.5B · Q4_K_M

Marginal

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score
80 vs 53
Hardware Fit
77 vs 89
Quality Score
81 vs 38

Hardware

qwen3.6:35b-mlx qwen2.5-0.5b-instr…
MachineMacBook ProLENOVO 20BUS00700
CPUApple M5 MaxIntel Core™ i5-5300U
Cores184
RAM48 GB16 GB
GPUApple M5 MaxIntel(R) HD Graphics 5500
OSmacOS 26.5.2Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.6:35b-mlx qwen2.5-0.5b-instr…
Tokens/sec129.813.2
First chunk77 ms1339 ms
TTFT30.0 s1.3 s
Load time1.8 sN/A
Memory usage19.7 GB0.4 GB
Memory %41%2%

HW Fit Score Breakdown

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

qwen2.5-0.5b-instruct

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

Quality

qwen3.6:35b-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong

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
View qwen3.6:35b-mlx details | View qwen2.5-0.5b-instr… 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