qwen3.5:35b-a3b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 22, 2026 · AMD RYZEN AI MAX+ 395
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
Global Score
88 vs 63
Hardware Fit
90 vs 62
Quality Score
87 vs 63
Hardware
qwen3.5:35b-a3b gemma4:12b
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM125 GB16 GB
GPURadeon 8060SApple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced
Performance
qwen3.5:35b-a3b gemma4:12b
Tokens/sec42.015.3
First chunk243 ms1142 ms
TTFT243 ms30.0 s
Load time9.7 s5.4 s
Memory usage32.1 GB7.6 GB
Memory %26%47%
HW Fit Score Breakdown
qwen3.5:35b-a3b
Speed
40/50
TTFT
20/20
Memory
30/30
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
Quality
qwen3.5:35b-a3b
Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:12b
Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
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