Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

ministral-3:8b

OLLAMA GGUF

mistral3 · 8.9B · Q4_K_M

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
53 vs 72
Hardware Fit
81 vs 71
Quality Score
41 vs 72

Hardware

qwen3.5:4b-mlx ministral-3:8b
MachineMac miniMacBook Pro
CPUApple M2Apple M1 Pro
Cores810
RAM8 GB16 GB
GPUApple M2Apple M1 Pro
OSmacOS 26.5.2macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx ministral-3:8b
Tokens/sec24.819.8
First chunk317 ms269 ms
TTFT7.4 s269 ms
Load time0.0 s10.7 s
Memory usage3.9 GB13.7 GB
Memory %49%86%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
25/30

ministral-3:8b

Speed
44/50
TTFT
20/20
Memory
7/30

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

ministral-3:8b

Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:4b-mlx details | View ministral-3:8b 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