Back to leaderboard

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Mar 7, 2026 · Intel Core™ i5-14600KF

gemma4:e4b-mlx

OLLAMA GGUF
Not Rec.

Jul 7, 2026 · Apple M2 Pro

Global Score
77 vs 78
Hardware Fit
53 vs 72
Quality Score
87 vs 81

Hardware

qwen3.5:35b gemma4:e4b-mlx
MachineASUSMacBook Pro
CPUIntel Core™ i5-14600KFApple M2 Pro
Cores2010
RAM32 GB16 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERApple M2 Pro
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.5
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b gemma4:e4b-mlx
Tokens/sec16.026.9
First chunk719 ms222 ms
TTFT719 ms222 ms
Load time17.8 s0.1 s
Memory usage25.0 GB15.4 GB
Memory %79%96%

HW Fit Score Breakdown

qwen3.5:35b

Speed
23/50
TTFT
20/20
Memory
10/30

gemma4:e4b-mlx

Speed
50/50
TTFT
20/20
Memory
2/30

Quality

qwen3.5:35b

Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gemma4:e4b-mlx

Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:35b details | View gemma4:e4b-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