qwen3.5:27b
OLLAMA GGUFqwen35 · 27.8B · Q4_K_M
Apr 1, 2026 · Apple M4
openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Sep 29, 2026 · Apple M5 Max
Global Score
4 vs 83
Hardware Fit
13 vs 80
Quality Score
0 vs 84
Hardware
qwen3.5:27b openai/gpt-oss-20b
MachineMac miniMacBook Pro
CPUApple M4Apple M5 Max
Cores1018
RAM24 GB128 GB
GPUApple M4Apple M5 Max
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:27b openai/gpt-oss-20b
Tokens/sec3.5138.4
First chunk1781 ms3 ms
TTFT52.0 s30.0 s
Load time13.4 s6.8 s
Memory usage21.3 GB0.5 GB
Memory %89%0%
HW Fit Score Breakdown
qwen3.5:27b
Speed
7/50
TTFT
0/20
Memory
6/30
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
qwen3.5:27b
Reasoning
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
openai/gpt-oss-20b
Reasoning
18/20
Coding
12/20
Instruction
15/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong 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