Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Oct 20, 2026 · Apple M1 Pro

gemma4:e2b

OLLAMA GGUF

gemma4 · 4.6B · Q4_K_M

Excellent

Oct 12, 2026 · AMD Ryzen 5 5500

Global Score
84 vs 93
Hardware Fit
78 vs 100
Quality Score
86 vs 90

Hardware

qwen/qwen3.6-35b-a3b gemma4:e2b
MachineMacBook ProMicrosoft WSL
CPUApple M1 ProAMD Ryzen 5 5500
Cores1012
RAM32 GB8 GB
GPUApple M1 ProIntegrated / Unknown
OSmacOS 15.6.1Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown

Performance

qwen/qwen3.6-35b-a3b gemma4:e2b
Tokens/sec49.9141.2
First chunk31 ms94 ms
TTFT708 ms1.6 s
Load timeN/A18.4 s
Memory usage26.6 GB0.2 GB
Memory %83%3%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
50/50
TTFT
20/20
Memory
8/30

gemma4:e2b

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

Quality

qwen/qwen3.6-35b-a3b

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gemma4:e2b

Reasoning
18/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen/qwen3.6-35b-a3b details | View gemma4:e2b 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