Back to leaderboard

qwen3.5-35b-a3b-mtp

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

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

gemma4:e4b-mlx

OLLAMA GGUF
Not Rec.

Jul 7, 2026 · Apple M2 Pro

Global Score
77 vs 78
Hardware Fit
51 vs 72
Quality Score
88 vs 81

Hardware

qwen3.5-35b-a3b-mtp gemma4:e4b-mlx
MachineDocker ContainerMacBook Pro
CPUIntel Gen Intel® Core™ i9-11900HApple M2 Pro
Cores1610
RAM15 GB16 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M2 Pro
OSUbuntu 26.04 LTSmacOS 26.5
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.5-35b-a3b-mtp gemma4:e4b-mlx
Tokens/sec7.826.9
First chunk30 ms222 ms
TTFT5.6 s222 ms
Load time32.5 s0.1 s
Memory usage0.0 GB15.4 GB
Memory %0%96%

HW Fit Score Breakdown

qwen3.5-35b-a3b-mtp

Speed
14/50
TTFT
7/20
Memory
30/30

gemma4:e4b-mlx

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

Quality

qwen3.5-35b-a3b-mtp

Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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-a3b-mtp 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