ministral-3-14b-instruct-2512

LM-STUDIO GGUF

mistral3 · 14B · Q5_K_M

Excellent

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

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

Global Score

83 vs 53

Hardware Fit

90 vs 72

Quality Score

80 vs 45

Hardware

ministral-3-14b-in… qwen3.5:9b

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 Modelow-powerbalanced

Performance

ministral-3-14b-in… qwen3.5:9b

Tokens/sec83.718.6

First chunk16 ms403 ms

TTFT117 ms10.2 s

Load timeN/A4.3 s

Memory usage18.2 GB9.1 GB

Memory %60%28%

HW Fit Score Breakdown

ministral-3-14b-instruc…

Speed

50/50

TTFT

20/20

Memory

20/30

qwen3.5:9b

Speed

38/50

TTFT

4/20

Memory

30/30

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

qwen3.5:9b

Reasoning

12/20

Coding

3/20

Instruction

5/20

Structured

6/15

Math

11/15

Multilingual

8/10

Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong

View ministral-3-14b-in… details | View qwen3.5:9b details

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