Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

Qwen3-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

Global Score
70 vs 87
Hardware Fit
93 vs 76
Quality Score
60 vs 91

Hardware

qwen3.5-2b-mlx Qwen3-80B:80B
MachineMacBook AirHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUApple M4NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1020
RAM32 GB55 GB
GPUApple M4NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-2b-mlx Qwen3-80B:80B
Tokens/sec32.943.6
First chunk3096 ms409 ms
TTFT3.1 s409 ms
Load timeN/A80.3 s
Memory usage2.5 GB48.0 GB
Memory %8%88%

HW Fit Score Breakdown

qwen3.5-2b-mlx

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

Qwen3-80B:80B

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

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

Qwen3-80B:80B

Reasoning
18/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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