Back to leaderboard

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 4bit

Marginal

Mar 3, 2026 · Apple M4

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Excellent

Jul 7, 2026 · Cortex-X925

Global Score
55 vs 83
Hardware Fit
87 vs 60
Quality Score
41 vs 93

Hardware

qwen3.5-0.8b-mlx gemma4:31b
MachineMacBook AirASUSTeK COMPUTER INC. GX10
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.5-0.8b-mlx gemma4:31b
Tokens/sec68.210.9
First chunk3268 ms681 ms
TTFT3.3 s681 ms
Load timeN/A16.6 s
Memory usage0.6 GB21.4 GB
Memory %2%18%

HW Fit Score Breakdown

qwen3.5-0.8b-mlx

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

gemma4:31b

Speed
10/50
TTFT
20/20
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

gemma4:31b

Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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