qwen3.5:35b-a3b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 6, 2026 · Apple M4 Pro
gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
Global Score
59 vs 81
Hardware Fit
69 vs 100
Quality Score
54 vs 73
Hardware
qwen3.5:35b-a3b gemma3n:latest
MachineMacBook ProSupermicro AS -2015HS-TNR
CPUApple M4 ProAMD EPYC 9654P 96-Core Processor
Cores1464
RAM48 GB128 GB
GPUApple M4 ProGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSmacOS 26.3.1Ubuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance
Performance
qwen3.5:35b-a3b gemma3n:latest
Tokens/sec30.5108.7
First chunk333 ms333 ms
TTFT30.0 s333 ms
Load time9.8 s4.5 s
Memory usage25.1 GB8.6 GB
Memory %52%7%
HW Fit Score Breakdown
qwen3.5:35b-a3b
Speed
45/50
TTFT
0/20
Memory
24/30
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:35b-a3b
Reasoning
18/20
Coding
1/20
Instruction
7/20
Structured
6/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong
gemma3n:latest
Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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