qwopus3.6-35b-a3b-coder-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
gemma4:e2b-mlx
OLLAMA GGUFAug 25, 2026 · Apple M1 Pro
Global Score
84 vs 82
Hardware Fit
79 vs 99
Quality Score
86 vs 75
Hardware
qwopus3.6-35b-a3b-… gemma4:e2b-mlx
MachineASUSMacBook Pro
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorApple M1 Pro
Cores1610
RAM31 GB16 GB
GPUNVIDIA GeForce RTX 4090, RaphaelApple M1 Pro
OScachyos rollingmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced
Performance
qwopus3.6-35b-a3b-… gemma4:e2b-mlx
Tokens/sec108.470.4
First chunk15 ms96 ms
TTFT319 ms96 ms
Load timeN/A2.5 s
Memory usage25.0 GB5.7 GB
Memory %82%36%
HW Fit Score Breakdown
qwopus3.6-35b-a3b-coder…
Speed
50/50
TTFT
20/20
Memory
9/30
gemma4:e2b-mlx
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwopus3.6-35b-a3b-coder…
Reasoning
16/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:e2b-mlx
Reasoning
14/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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