Back to leaderboard

qwen3.5:27b

qwen35 · 27.8B · Q4_K_M

Good

Mar 3, 2026 · Apple M4

smollm2:135m

llama · 134.52M · F16

Marginal

Mar 2, 2026 · Apple M4

Global Score
75 vs 41
Hardware Fit
67 vs 100
Quality Score
79 vs 15

Hardware

qwen3.5:27b smollm2:135m
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:27b smollm2:135m
Tokens/sec4.4241.0
TTFT1.1 s39 ms
Load time13.2 s0.4 s
Memory usage22.7 GB0.6 GB
Memory %71%2%

HW Fit Score Breakdown

qwen3.5:27b

Speed
7/40
TTFT
30/30
Memory
30/30

smollm2:135m

Speed
40/40
TTFT
30/30
Memory
30/30

Quality

qwen3.5:27b

Reasoning
16/20
Coding
17/20
Instruction
9/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong

smollm2:135m

Reasoning
4/20
Coding
1/20
Instruction
6/20
Structured
2/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3.5:27b details | View smollm2:135m details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running