gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K
Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
85 vs 88
Hardware Fit
77 vs 94
Quality Score
89 vs 85
Hardware
gemma4:26b huihui-qwen3.6-35b…
MachineMac miniGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M4AMD Ryzen 5 5600X 6-Core Processor
Cores1012
RAM24 GB47 GB
GPUApple M4AD106 [GeForce RTX 4060 Ti]
OSmacOS 26.3cachyos rolling
Archarm64x64
Power Modebalancedlow-power
Performance
gemma4:26b huihui-qwen3.6-35b…
Tokens/sec24.539.8
First chunk1481 ms3 ms
TTFT1.5 s479 ms
Load time24.7 sN/A
Memory usage20.3 GB24.4 GB
Memory %85%52%
HW Fit Score Breakdown
gemma4:26b
Speed
49/50
TTFT
20/20
Memory
8/30
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
20/20
Memory
24/30
Quality
gemma4:26b
Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest