Back to leaderboard

mlx-community/stablelm-2-zephyr-1_6b-4bit

LM-STUDIO GGUF
Marginal

Mar 5, 2026 · Apple M4

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
50 vs 65
Hardware Fit
100 vs 73
Quality Score
29 vs 62

Hardware

mlx-community/stab… qwen3.5:4b
MachineMacBook AirAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM32 GB125 GB
GPUApple M4AMD Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

mlx-community/stab… qwen3.5:4b
Tokens/sec93.645.7
First chunk166 ms180 ms
TTFT166 ms30.0 s
Load timeN/A5.3 s
Memory usage0.7 GB16.2 GB
Memory %2%13%

HW Fit Score Breakdown

mlx-community/stablelm-…

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

qwen3.5:4b

Speed
43/50
TTFT
0/20
Memory
30/30

Quality

mlx-community/stablelm-…

Reasoning
7/20
Coding
2/20
Instruction
9/20
Structured
3/15
Math
4/15
Multilingual
4/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Weak

qwen3.5:4b

Reasoning
17/20
Coding
1/20
Instruction
13/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong 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