qwen/qwen3.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q6_K
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
72 vs 91
Hardware Fit
35 vs 96
Quality Score
88 vs 89
Hardware
qwen/qwen3.5-35b-a3b gemma4:12b-mlx
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M2 Pro
Cores1610
RAM32 GB16 GB
GPUAMD Radeon RX 9060 XTApple M2 Pro
OSMicrosoft Windows 11 Home 10.0.26200macOS 26.5
Archx64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.5-35b-a3b gemma4:12b-mlx
Tokens/sec8.324.7
First chunk32 ms610 ms
TTFT2.0 s610 ms
Load timeN/A3.6 s
Memory usage28.9 GB7.1 GB
Memory %91%45%
HW Fit Score Breakdown
qwen/qwen3.5-35b-a3b
Speed
13/50
TTFT
17/20
Memory
5/30
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
qwen/qwen3.5-35b-a3b
Reasoning
16/20
Coding
19/20
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
gemma4:12b-mlx
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
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