Back to leaderboard

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
50 vs 88
Hardware Fit
97 vs 94
Quality Score
30 vs 85

Hardware

gemma3:270m huihui-qwen3.6-35b…
MachineMacBook ProGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M3 ProAMD Ryzen 5 5600X 6-Core Processor
Cores1212
RAM36 GB47 GB
GPUApple M3 ProAD106 [GeForce RTX 4060 Ti]
OSmacOS 15.7.5cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

gemma3:270m huihui-qwen3.6-35b…
Tokens/sec239.239.8
First chunk127 ms3 ms
TTFT127 ms479 ms
Load time0.7 sN/A
Memory usage0.6 GB24.4 GB
Memory %2%52%

HW Fit Score Breakdown

gemma3:270m

Speed
50/50
TTFT
20/20
Memory
27/30

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
20/20
Memory
24/30

Quality

gemma3:270m

Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
8/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak

huihui-qwen3.6-35b-a3b-…

Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest