qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_S
Apr 20, 2026 · Apple M2 Max
granite3.1-moe:3b
OLLAMA GGUFgranitemoe · 3.3B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
82 vs 66
Hardware Fit
80 vs 99
Quality Score
83 vs 52
Hardware
qwen3.6-35b-a3b granite3.1-moe:3b
MachineMac StudioDell Inc. Inspiron 15 3530
CPUApple M2 MaxIntel Gen Intel® Core™ i7-1355U
Cores1212
RAM96 GB31 GB
GPUApple M2 MaxRaptor Lake-P [Iris Xe Graphics]
OSmacOS 26.1cachyos rolling
Archarm64x64
Power Modebalancedlow-power
Performance
qwen3.6-35b-a3b granite3.1-moe:3b
Tokens/sec55.227.2
First chunk4 ms527 ms
TTFT30.0 s527 ms
Load timeN/A1.9 s
Memory usage30.3 GB2.9 GB
Memory %32%9%
HW Fit Score Breakdown
qwen3.6-35b-a3b
Speed
50/50
TTFT
0/20
Memory
30/30
granite3.1-moe:3b
Speed
49/50
TTFT
20/20
Memory
30/30
Quality
qwen3.6-35b-a3b
Reasoning
18/20
Coding
10/20
Instruction
18/20
Structured
14/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
granite3.1-moe:3b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
5/15
Multilingual
6/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest