Back to leaderboard

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

ministral-3-14b-instruct-2512

LM-STUDIO GGUF

mistral3 · 14B · Q5_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
65 vs 83
Hardware Fit
96 vs 90
Quality Score
51 vs 80

Hardware

qwen3-4b-qwen3.6-p… ministral-3-14b-in…
MachineMac StudioASUS
CPUApple M2 MaxAMD Ryzen 7 7800X3D 8-Core Processor
Cores1216
RAM96 GB31 GB
GPUApple M2 MaxNVIDIA GeForce RTX 4090, Raphael
OSmacOS 26.1cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3-4b-qwen3.6-p… ministral-3-14b-in…
Tokens/sec99.683.7
First chunk18 ms16 ms
TTFT1.6 s117 ms
Load time4.8 sN/A
Memory usage0.3 GB18.2 GB
Memory %0%60%

HW Fit Score Breakdown

qwen3-4b-qwen3.6-plus-r…

Speed
50/50
TTFT
16/20
Memory
30/30

ministral-3-14b-instruc…

Speed
50/50
TTFT
20/20
Memory
20/30

Quality

qwen3-4b-qwen3.6-plus-r…

Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

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

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest