Back to leaderboard

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 4bit

Marginal

Mar 6, 2026 · Apple M4 Pro

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

Global Score
53 vs 81
Hardware Fit
89 vs 100
Quality Score
38 vs 73

Hardware

qwen3.5-0.8b-mlx gemma3n:latest
MachineMac miniSupermicro AS -2015HS-TNR
CPUApple M4 ProAMD EPYC 9654P 96-Core Processor
Cores1464
RAM64 GB128 GB
GPUApple M4 ProGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSmacOS 15.7.4Ubuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.5-0.8b-mlx gemma3n:latest
Tokens/sec52.9108.7
First chunk4013 ms333 ms
TTFT4.0 s333 ms
Load timeN/A4.5 s
Memory usage0.6 GB8.6 GB
Memory %1%7%

HW Fit Score Breakdown

qwen3.5-0.8b-mlx

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

gemma3n:latest

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

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

gemma3n:latest

Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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