Back to leaderboard

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

gemma4:12b-mlx

OLLAMA GGUF
Not Rec.

Aug 24, 2026 · Apple M1 Pro

Global Score
79 vs 71
Hardware Fit
59 vs 76
Quality Score
87 vs 69

Hardware

qwen3.6-35b-a3b gemma4:12b-mlx
MachineDocker ContainerMacBook Pro
CPUIntel Gen Intel® Core™ i9-11900HApple M1 Pro
Cores1610
RAM15 GB16 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M1 Pro
OSUbuntu 26.04 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.6-35b-a3b gemma4:12b-mlx
Tokens/sec9.325.0
First chunk21 ms787 ms
TTFT3.6 s30.0 s
Load time32.0 s4.0 s
Memory usage1.8 GB7.1 GB
Memory %12%45%

HW Fit Score Breakdown

qwen3.6-35b-a3b

Speed
17/50
TTFT
12/20
Memory
30/30

gemma4:12b-mlx

Speed
50/50
TTFT
0/20
Memory
26/30

Quality

qwen3.6-35b-a3b

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

gemma4:12b-mlx

Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.6-35b-a3b details | View gemma4:12b-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