Back to leaderboard

llama3.2:3b

llama · 3.2B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

smollm2:1.7b

llama · 1.7B · Q8_0

Good

Mar 1, 2026 · Apple M4

Global Score
78 vs 63
Hardware Fit
100 vs 99
Quality Score
63 vs 39

Hardware

llama3.2:3b smollm2:1.7b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

llama3.2:3b smollm2:1.7b
Tokens/sec44.150.3
TTFT178 ms81 ms
Load time0.8 s0.4 s
Memory usage7.0 GB3.7 GB
Memory %22%12%

HW Fit Score Breakdown

llama3.2:3b

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

smollm2:1.7b

Speed
40/40
TTFT
30/30
Memory
29/30

Quality

llama3.2:3b

Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

smollm2:1.7b

Reasoning
7/20
Coding
0/20
Instruction
12/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View llama3.2:3b details | View smollm2:1.7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running