Back to leaderboard

microllm-50m:latest

OLLAMA GGUF

llama · 49.31M · F16

Not Rec.

Jun 28, 2026 · Apple M4 Pro

qwen3:32b

OLLAMA GGUF

qwen3 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
28 vs 79
Hardware Fit
80 vs 59
Quality Score
5 vs 88

Hardware

microllm-50m:latest qwen3:32b
MachineMac miniNVIDIA NVIDIA_DGX_Spark
CPUApple M4 ProCortex-X925
Cores1220
RAM24 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.6.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

microllm-50m:latest qwen3:32b
Tokens/sec1000000.09.7
First chunk50 ms324 ms
TTFT30.0 s324 ms
Load time0.3 s24.5 s
Memory usage0.1 GB26.8 GB
Memory %1%22%

HW Fit Score Breakdown

microllm-50m:latest

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

qwen3:32b

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

Quality

microllm-50m:latest

Reasoning
0/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

qwen3:32b

Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View microllm-50m:latest details | View qwen3:32b 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