Back to leaderboard

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 4bit

Marginal

Mar 3, 2026 · Apple M4

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

Global Score
55 vs 47
Hardware Fit
87 vs 53
Quality Score
41 vs 45

Hardware

qwen3.5-0.8b-mlx qwen3:4b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedunknown

Performance

qwen3.5-0.8b-mlx qwen3:4b
Tokens/sec68.211.3
First chunk3268 msN/A
TTFT3.3 s9.2 s
Load timeN/A0.1 s
Memory usage0.6 GB7.2 GB
Memory %2%23%

HW Fit Score Breakdown

qwen3.5-0.8b-mlx

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

qwen3:4b

Speed
17/50
TTFT
6/20
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

qwen3:4b

Reasoning
4/20
Coding
6/20
Instruction
8/20
Structured
6/15
Math
12/15
Multilingual
9/10
Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong
View qwen3.5-0.8b-mlx details | View qwen3:4b 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