ministral-3-14b-instruct-2512
LM-STUDIO GGUFmistral3 · 14B · Q5_K_M
Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K
Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
83 vs 88
Hardware Fit
90 vs 85
Quality Score
80 vs 89
Hardware
ministral-3-14b-in… huihui-qwen3.6-35b…
MachineASUSGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD Ryzen 5 5600X 6-Core Processor
Cores1612
RAM31 GB47 GB
GPUNVIDIA GeForce RTX 4090, RaphaelAD106 [GeForce RTX 4060 Ti]
OScachyos rollingcachyos rolling
Archx64x64
Power Modelow-powerlow-power
Performance
ministral-3-14b-in… huihui-qwen3.6-35b…
Tokens/sec83.737.7
First chunk16 ms18 ms
TTFT117 ms2.9 s
Load timeN/AN/A
Memory usage18.2 GB26.1 GB
Memory %60%56%
HW Fit Score Breakdown
ministral-3-14b-instruc…
Speed
50/50
TTFT
20/20
Memory
20/30
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
13/20
Memory
22/30
Quality
ministral-3-14b-instruc…
Reasoning
17/20
Coding
17/20
Instruction
15/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
huihui-qwen3.6-35b-a3b-…
Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
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