qwen3.5-27b
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Mar 3, 2026 · Apple M4
llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
Global Score
75 vs 67
Hardware Fit
54 vs 77
Quality Score
84 vs 63
Hardware
qwen3.5-27b llama3.2:3b
MachineMacBook AirLENOVO 20U30029MB
CPUApple M4Intel Core™ i5-10210U
Cores108
RAM32 GB15 GB
GPUApple M4CometLake-U GT2 [UHD Graphics]
OSmacOS 26.3Pop 24.04 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
qwen3.5-27b llama3.2:3b
Tokens/sec6.610.0
First chunk4364 ms1166 ms
TTFT4.4 s1.2 s
Load timeN/A6.8 s
Memory usage15.0 GB3.8 GB
Memory %47%25%
HW Fit Score Breakdown
qwen3.5-27b
Speed
13/50
TTFT
11/20
Memory
30/30
llama3.2:3b
Speed
27/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5-27b
Reasoning
17/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
llama3.2:3b
Reasoning
11/20
Coding
15/20
Instruction
13/20
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