gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
Global Score
81 vs 80
Hardware Fit
100 vs 77
Quality Score
73 vs 81
Hardware
gemma3n:latest qwen3.6:35b-mlx
MachineSupermicro AS -2015HS-TNRMacBook Pro
CPUAMD EPYC 9654P 96-Core ProcessorApple M5 Max
Cores6418
RAM128 GB48 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Apple M5 Max
OSUbuntu 24.04.3 LTSmacOS 26.5.2
Archx64arm64
Power Modeperformancebalanced
Performance
gemma3n:latest qwen3.6:35b-mlx
Tokens/sec108.7129.8
First chunk333 ms77 ms
TTFT333 ms30.0 s
Load time4.5 s1.8 s
Memory usage8.6 GB19.7 GB
Memory %7%41%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
Quality
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
qwen3.6:35b-mlx
Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong 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