Back to leaderboard

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 4bit

Marginal

Mar 6, 2026 · Apple M4 Pro

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K

Global Score
53 vs 80
Hardware Fit
89 vs 60
Quality Score
38 vs 88

Hardware

qwen3.5-0.8b-mlx qwen3-coder:30b
MachineMac miniASUS
CPUApple M4 ProIntel Gen Intel® Core™ i7-12700K
Cores1420
RAM64 GB96 GB
GPUApple M4 ProParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSmacOS 15.7.4Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-0.8b-mlx qwen3-coder:30b
Tokens/sec52.914.7
First chunk4013 ms796 ms
TTFT4.0 s796 ms
Load timeN/A0.2 s
Memory usage0.6 GB17.9 GB
Memory %1%19%

HW Fit Score Breakdown

qwen3.5-0.8b-mlx

Speed
50/50
TTFT
9/20
Memory
30/30

qwen3-coder:30b

Speed
14/50
TTFT
19/20
Memory
27/30

Quality

qwen3.5-0.8b-mlx

Reasoning
7/20
Coding
2/20
Instruction
12/20
Structured
10/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate

qwen3-coder:30b

Reasoning
17/20
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
View qwen3.5-0.8b-mlx details | View qwen3-coder:30b 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