Back to leaderboard

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Apr 29, 2026 · Intel Core™ i5-8350U

qwen3.5:9b-mlx

OLLAMA GGUF

nvfp4

Excellent

Aug 25, 2026 · Apple M1 Pro

Global Score
61 vs 84
Hardware Fit
85 vs 94
Quality Score
51 vs 80

Hardware

qwen3:0.6b qwen3.5:9b-mlx
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M1 Pro
Cores810
RAM23 GB16 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M1 Pro
OSFedora Linux 43macOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3:0.6b qwen3.5:9b-mlx
Tokens/sec27.025.0
First chunk597 ms357 ms
TTFT8.7 s357 ms
Load time1.8 s3.8 s
Memory usage0.9 GB8.4 GB
Memory %4%52%

HW Fit Score Breakdown

qwen3:0.6b

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

qwen3.5:9b-mlx

Speed
50/50
TTFT
20/20
Memory
24/30

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

qwen3.5:9b-mlx

Reasoning
16/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3:0.6b details | View qwen3.5:9b-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