qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
Feb 28, 2026 · Apple M4 Pro
Global Score
34 vs 73
Hardware Fit
58 vs 100
Quality Score
23 vs 61
Hardware
qwen3.5:latest llama3.2:latest
MachineMac miniMac Mini
CPUApple M4Apple M4 Pro
Cores1014
RAM16 GB64 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.7.4
Archarm64arm64
Power Modebalancedunknown
Performance
qwen3.5:latest llama3.2:latest
Tokens/sec13.398.9
First chunk438 msN/A
TTFT19.8 s125 ms
Load time0.2 s2.3 s
Memory usage8.0 GB22.1 GB
Memory %50%35%
HW Fit Score Breakdown
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
llama3.2:latest
Speed
40/50
TTFT
30/20
Memory
30/30
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
llama3.2:latest
Reasoning
11/20
Coding
14/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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