qwen3.6:35b-a3b-q8_0
OLLAMA GGUFqwen35moe · 36.0B · Q8_0
Jul 7, 2026 · Cortex-X925
gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
Global Score
91 vs 85
Hardware Fit
99 vs 77
Quality Score
87 vs 89
Hardware
qwen3.6:35b-a3b-q8_0 gemma4:26b
MachineASUSTeK COMPUTER INC. GX10Mac mini
CPUCortex-X925Apple M4
Cores2010
RAM122 GB24 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen3.6:35b-a3b-q8_0 gemma4:26b
Tokens/sec56.224.5
First chunk531 ms1481 ms
TTFT531 ms1.5 s
Load time32.8 s24.7 s
Memory usage41.0 GB20.3 GB
Memory %34%85%
HW Fit Score Breakdown
qwen3.6:35b-a3b-q8_0
Speed
50/50
TTFT
20/20
Memory
29/30
gemma4:26b
Speed
49/50
TTFT
20/20
Memory
8/30
Quality
qwen3.6:35b-a3b-q8_0
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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
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