Back to leaderboard

qwen3:0.6b

qwen3 · 751.63M · Q4_K_M

Good

Mar 2, 2026 · Apple M4

llama-3.2-3b-instruct

llama · 3B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
61 vs 72
Hardware Fit
100 vs 100
Quality Score
44 vs 60

Hardware

qwen3:0.6b llama-3.2-3b-instr…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3:0.6b llama-3.2-3b-instr…
Tokens/sec144.348.2
TTFT81 ms265 ms
Load time0.9 s0.0 s
Memory usage4.1 GB0.0 GB
Memory %13%0%

HW Fit Score Breakdown

qwen3:0.6b

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

llama-3.2-3b-instruct

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

Quality

qwen3:0.6b

Reasoning
6/20
Coding
4/20
Instruction
10/20
Structured
13/15
Math
6/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Weak

llama-3.2-3b-instruct

Reasoning
9/20
Coding
13/20
Instruction
14/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3:0.6b details | View llama-3.2-3b-instr… details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running