Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
53 vs 61
Hardware Fit
81 vs 85
Quality Score
41 vs 51

Hardware

qwen3.5:4b-mlx qwen3:0.6b
MachineMac miniLENOVO 20L7CTO1WW
CPUApple M2Intel Core™ i5-8350U
Cores88
RAM8 GB23 GB
GPUApple M2Kaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.5.2Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3.5:4b-mlx qwen3:0.6b
Tokens/sec24.827.0
First chunk317 ms597 ms
TTFT7.4 s8.7 s
Load time0.0 s1.8 s
Memory usage3.9 GB0.9 GB
Memory %49%4%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
25/30

qwen3:0.6b

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

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

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
View qwen3.5:4b-mlx details | View qwen3:0.6b 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