qwopus3.6-35b-a3b-coder-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
Global Score
84 vs 90
Hardware Fit
79 vs 97
Quality Score
86 vs 87
Hardware
qwopus3.6-35b-a3b-… qwen3:14b
MachineASUSMacBook Pro
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorApple M1 Max
Cores1610
RAM31 GB32 GB
GPUNVIDIA GeForce RTX 4090, RaphaelApple M1 Max
OScachyos rollingmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
qwopus3.6-35b-a3b-… qwen3:14b
Tokens/sec108.424.0
First chunk15 ms300 ms
TTFT319 ms300 ms
Load timeN/A3.6 s
Memory usage25.0 GB13.8 GB
Memory %82%43%
HW Fit Score Breakdown
qwopus3.6-35b-a3b-coder…
Speed
50/50
TTFT
20/20
Memory
9/30
qwen3:14b
Speed
47/50
TTFT
20/20
Memory
30/30
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
qwen3:14b
Reasoning
17/20
Coding
18/20
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