Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

huihui_ai/Qwen3.8-abliterated:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Aug 25, 2026 · AMD RYZEN AI MAX+ 395

Global Score
70 vs 80
Hardware Fit
93 vs 65
Quality Score
60 vs 87

Hardware

qwen3.5-2b-mlx huihui_ai/Qwen3.8-…
MachineMacBook AirAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM32 GB125 GB
GPUApple M4Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3.5-2b-mlx huihui_ai/Qwen3.8-…
Tokens/sec32.917.5
First chunk3096 ms597 ms
TTFT3.1 s597 ms
Load timeN/A7.1 s
Memory usage2.5 GB17.4 GB
Memory %8%14%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed
50/50
TTFT
13/20
Memory
30/30

huihui_ai/Qwen3.8-ablit…

Speed
16/50
TTFT
19/20
Memory
30/30

Quality

qwen3.5-2b-mlx

Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

huihui_ai/Qwen3.8-ablit…

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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