qwen/qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
80 vs 78
Hardware Fit
60 vs 72
Quality Score
88 vs 81
Hardware
qwen/qwen3.6-35b-a3b gemma4:e4b-mlx
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M2 Pro
Cores1610
RAM31 GB16 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M2 Pro
OSUbuntu 26.04.1 LTSmacOS 26.5
Archx64arm64
Power Modeperformancebalanced
Performance
qwen/qwen3.6-35b-a3b gemma4:e4b-mlx
Tokens/sec15.026.9
First chunk49 ms222 ms
TTFT759 ms222 ms
Load timeN/A0.1 s
Memory usage22.2 GB15.4 GB
Memory %71%96%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
25/50
TTFT
20/20
Memory
15/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
2/30
Quality
qwen/qwen3.6-35b-a3b
Reasoning
16/20
Coding
18/20
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
gemma4:e4b-mlx
Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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