Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 6bit

Excellent

Jul 17, 2026 · Apple M5 Max

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
87 vs 76
Hardware Fit
90 vs 92
Quality Score
86 vs 69

Hardware

qwen/qwen3.6-35b-a3b gemma3:4b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M5 MaxCortex-A78AE
Cores186
RAM64 GB7 GB
GPUApple M5 MaxIntegrated / Unknown
OSmacOS 27.0Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.6-35b-a3b gemma3:4b
Tokens/sec86.515.0
First chunk9 ms2380 ms
TTFT175 ms2.4 s
Load timeN/A13.6 s
Memory usage37.9 GB2.6 GB
Memory %59%35%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

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

gemma3:4b

Speed
45/50
TTFT
18/20
Memory
29/30

Quality

qwen/qwen3.6-35b-a3b

Reasoning
16/20
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

gemma3:4b

Reasoning
11/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

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