Back to leaderboard

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 4bit

Marginal

Mar 3, 2026 · Apple M4

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Not Rec.

Aug 22, 2026 · Apple M1 Pro

Global Score
55 vs 63
Hardware Fit
87 vs 62
Quality Score
41 vs 63

Hardware

qwen3.5-0.8b-mlx gemma4:12b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-0.8b-mlx gemma4:12b
Tokens/sec68.215.3
First chunk3268 ms1142 ms
TTFT3.3 s30.0 s
Load timeN/A5.4 s
Memory usage0.6 GB7.6 GB
Memory %2%47%

HW Fit Score Breakdown

qwen3.5-0.8b-mlx

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

gemma4:12b

Speed
36/50
TTFT
0/20
Memory
26/30

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

gemma4:12b

Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak 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