Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M4

gpt-oss-orchestrator:latest

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Mar 19, 2026 · Apple M4

Global Score
48 vs 88
Hardware Fit
77 vs 80
Quality Score
35 vs 91

Hardware

qwen3.5:4b gpt-oss-orchestrat…
MachineMac miniMac mini
CPUApple M4Apple M4
Cores1010
RAM16 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b gpt-oss-orchestrat…
Tokens/sec18.924.6
First chunk316 ms525 ms
TTFT13.0 s4.8 s
Load time3.7 s8.5 s
Memory usage5.9 GB13.8 GB
Memory %37%58%

HW Fit Score Breakdown

qwen3.5:4b

Speed
43/50
TTFT
4/20
Memory
30/30

gpt-oss-orchestrator:la…

Speed
49/50
TTFT
10/20
Memory
21/30

Quality

qwen3.5:4b

Reasoning
10/20
Coding
1/20
Instruction
4/20
Structured
3/15
Math
8/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Strong

gpt-oss-orchestrator:la…

Reasoning
19/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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