qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
Global Score
34 vs 88
Hardware Fit
58 vs 80
Quality Score
23 vs 91
Hardware
qwen3.5:latest 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:latest gpt-oss-orchestrat…
Tokens/sec13.324.6
First chunk438 ms525 ms
TTFT19.8 s4.8 s
Load time0.2 s8.5 s
Memory usage8.0 GB13.8 GB
Memory %50%58%
HW Fit Score Breakdown
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
Quality
qwen3.5:latest
Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak 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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest