Back to leaderboard

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Apr 29, 2026 · Intel Core™ i5-8350U

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
61 vs 80
Hardware Fit
85 vs 77
Quality Score
51 vs 81

Hardware

qwen3:0.6b qwen3.6:35b-mlx
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M5 Max
Cores818
RAM23 GB48 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M5 Max
OSFedora Linux 43macOS 26.5.2
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3:0.6b qwen3.6:35b-mlx
Tokens/sec27.0129.8
First chunk597 ms77 ms
TTFT8.7 s30.0 s
Load time1.8 s1.8 s
Memory usage0.9 GB19.7 GB
Memory %4%41%

HW Fit Score Breakdown

qwen3:0.6b

Speed
50/50
TTFT
5/20
Memory
30/30

qwen3.6:35b-mlx

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

Quality

qwen3:0.6b

Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate

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
View qwen3:0.6b details | View qwen3.6:35b-mlx 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