Back to leaderboard

qwen3.5:2b

OLLAMA GGUF

qwen35 · 2.3B · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
13 vs 89
Hardware Fit
41 vs 97
Quality Score
1 vs 86

Hardware

qwen3.5:2b 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

qwen3.5:2b qwen3.6:35b-mlx
Tokens/sec4.5129.4
First chunk1413 ms49 ms
TTFT31.1 s49 ms
Load time7.1 s0.0 s
Memory usage3.8 GB20.5 GB
Memory %16%43%

HW Fit Score Breakdown

qwen3.5:2b

Speed
11/50
TTFT
0/20
Memory
30/30

qwen3.6:35b-mlx

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

Quality

qwen3.5:2b

Reasoning
0/20
Coding
0/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen3.6:35b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:2b 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