Back to leaderboard

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

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

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

Global Score
79 vs 85
Hardware Fit
59 vs 64
Quality Score
87 vs 94

Hardware

qwen3.6-35b-a3b gemma-4-31b-it-mlx
MachineDocker ContainerMacBook Pro
CPUIntel Gen Intel® Core™ i9-11900HApple M4 Max
Cores1616
RAM15 GB128 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M4 Max
OSUbuntu 26.04 LTSmacOS 26.5.2
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.6-35b-a3b gemma-4-31b-it-mlx
Tokens/sec9.313.6
First chunk21 ms16 ms
TTFT3.6 s558 ms
Load time32.0 s12.3 s
Memory usage1.8 GB0.0 GB
Memory %12%0%

HW Fit Score Breakdown

qwen3.6-35b-a3b

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

gemma-4-31b-it-mlx

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

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

gemma-4-31b-it-mlx

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.6-35b-a3b details | View gemma-4-31b-it-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