Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Qwen3-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

Global Score
65 vs 62
Hardware Fit
88 vs 10
Quality Score
55 vs 84

Hardware

qwen3.5-2b-mlx Qwen3-80B:80B
MachineMac miniHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUApple M4 ProAMD Ryzen 9 9955HX3D 16-Core Processor
Cores1432
RAM64 GB31 GB
GPUApple M4 ProAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSmacOS 15.7.4Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-2b-mlx Qwen3-80B:80B
Tokens/sec48.94.9
First chunk4208 ms8006 ms
TTFT4.2 s8.0 s
Load timeN/A63.7 s
Memory usage1.6 GB47.3 GB
Memory %3%153%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

Qwen3-80B:80B

Speed
6/50
TTFT
4/20
Memory
0/30

Quality

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

Qwen3-80B:80B

Reasoning
17/20
Coding
19/20
Instruction
13/20
Structured
13/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5-2b-mlx details | View Qwen3-80B:80B 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