Back to leaderboard

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Not Rec.

Apr 1, 2026 · Apple M4

tinyllama

OLLAMA GGUF
Marginal

Mar 6, 2026 · Apple M4

Global Score
4 vs 43
Hardware Fit
13 vs 100
Quality Score
0 vs 19

Hardware

qwen3.5:27b tinyllama
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:27b tinyllama
Tokens/sec3.5133.4
First chunk1781 ms61 ms
TTFT52.0 s61 ms
Load time13.4 s0.5 s
Memory usage21.3 GB0.2 GB
Memory %89%1%

HW Fit Score Breakdown

qwen3.5:27b

Speed
7/50
TTFT
0/20
Memory
6/30

tinyllama

Speed
50/50
TTFT
20/20
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

tinyllama

Reasoning
2/20
Coding
2/20
Instruction
7/20
Structured
5/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
View qwen3.5:27b details | View tinyllama details

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