qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
Global Score
89 vs 81
Hardware Fit
97 vs 100
Quality Score
86 vs 73
Hardware
qwen/qwen3.6-35b-a3b gemma3n:latest
MachineMacBook ProSupermicro AS -2015HS-TNR
CPUApple M5 MaxAMD EPYC 9654P 96-Core Processor
Cores1864
RAM64 GB128 GB
GPUApple M5 MaxGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSmacOS 27.0Ubuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance
Performance
qwen/qwen3.6-35b-a3b gemma3n:latest
Tokens/sec130.2108.7
First chunk5 ms333 ms
TTFT135 ms333 ms
Load timeN/A4.5 s
Memory usage26.6 GB8.6 GB
Memory %42%7%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
gemma3n:latest
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
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