Back to leaderboard

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 8bit

Good

Mar 3, 2026 · Apple M4

granite3.1-moe:3b

OLLAMA GGUF

granitemoe · 3.3B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

Global Score
60 vs 66
Hardware Fit
96 vs 99
Quality Score
44 vs 52

Hardware

qwen3.5-0.8b-mlx granite3.1-moe:3b
MachineMacBook AirDell Inc. Inspiron 15 3530
CPUApple M4Intel Gen Intel® Core™ i7-1355U
Cores1012
RAM32 GB31 GB
GPUApple M4Raptor Lake-P [Iris Xe Graphics]
OSmacOS 26.3cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3.5-0.8b-mlx granite3.1-moe:3b
Tokens/sec108.027.2
First chunk2568 ms527 ms
TTFT2.6 s527 ms
Load timeN/A1.9 s
Memory usage1.0 GB2.9 GB
Memory %3%9%

HW Fit Score Breakdown

qwen3.5-0.8b-mlx

Speed
50/50
TTFT
16/20
Memory
30/30

granite3.1-moe:3b

Speed
49/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5-0.8b-mlx

Reasoning
10/20
Coding
3/20
Instruction
11/20
Structured
12/15
Math
3/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

granite3.1-moe:3b

Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
5/15
Multilingual
6/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate

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