Back to leaderboard

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 4bit

Marginal

Mar 3, 2026 · Apple M4

qwen3-coder:30b-a3b-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 18, 2026 · Intel Core™ Ultra 9 285HX

Global Score
55 vs 91
Hardware Fit
87 vs 100
Quality Score
41 vs 87

Hardware

qwen3.5-0.8b-mlx qwen3-coder:30b-a3…
MachineMacBook AirMicro-Star International Co., Ltd. Titan 18 HX AI A2XWJG
CPUApple M4Intel Core™ Ultra 9 285HX
Cores1024
RAM32 GB63 GB
GPUApple M4Intel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPU
OSmacOS 26.3Microsoft Windows 11 Home Single Language 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-0.8b-mlx qwen3-coder:30b-a3…
Tokens/sec68.2175.3
First chunk3268 ms224 ms
TTFT3.3 s224 ms
Load timeN/A6.1 s
Memory usage0.6 GB18.7 GB
Memory %2%30%

HW Fit Score Breakdown

qwen3.5-0.8b-mlx

Speed
50/50
TTFT
13/20
Memory
24/30

qwen3-coder:30b-a3b-q4_…

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

Quality

qwen3.5-0.8b-mlx

Reasoning
8/20
Coding
1/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

qwen3-coder:30b-a3b-q4_…

Reasoning
16/20
Coding
19/20
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