qwen/qwen3.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q6_K
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
unsloth/gemma-4-26b-a4b-it
LM-STUDIO GGUFgemma4 · 26B · Q3_K_M
Apr 5, 2026 · Apple M4
Global Score
72 vs 90
Hardware Fit
35 vs 85
Quality Score
88 vs 92
Hardware
qwen/qwen3.5-35b-a3b unsloth/gemma-4-26…
MachineSystem manufacturerMac mini
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M4
Cores1610
RAM32 GB24 GB
GPUAMD Radeon RX 9060 XTApple M4
OSMicrosoft Windows 11 Home 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.5-35b-a3b unsloth/gemma-4-26…
Tokens/sec8.324.9
First chunk32 ms15 ms
TTFT2.0 s817 ms
Load timeN/AN/A
Memory usage28.9 GB16.8 GB
Memory %91%70%
HW Fit Score Breakdown
qwen/qwen3.5-35b-a3b
Speed
13/50
TTFT
17/20
Memory
5/30
unsloth/gemma-4-26b-a4b…
Speed
50/50
TTFT
20/20
Memory
15/30
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
unsloth/gemma-4-26b-a4b…
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
14/15
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