gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
qwen/qwen3.6-35b-a3b:2
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
85 vs 73
Hardware Fit
95 vs 50
Quality Score
81 vs 83
Hardware
gemma4:e4b-mlx qwen/qwen3.6-35b-a…
MachineMacBook ProSystem manufacturer
CPUApple M2 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1016
RAM16 GB31 GB
GPUApple M2 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.5Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
gemma4:e4b-mlx qwen/qwen3.6-35b-a…
Tokens/sec47.310.5
First chunk258 ms4 ms
TTFT258 ms1.7 s
Load time5.1 sN/A
Memory usage7.9 GB21.4 GB
Memory %49%69%
HW Fit Score Breakdown
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
qwen/qwen3.6-35b-a3b:2
Speed
16/50
TTFT
18/20
Memory
16/30
Quality
gemma4:e4b-mlx
Reasoning
15/20
Coding
18/20
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
qwen/qwen3.6-35b-a3b:2
Reasoning
16/20
Coding
15/20
Instruction
15/20
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