Back to leaderboard

falcon3-1b-instruct

LM-STUDIO MLX

llama · 1B · 3bit

Marginal

Mar 4, 2026 · Apple M4

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Excellent

Mar 2, 2026 · Apple M4

Global Score
54 vs 80
Hardware Fit
100 vs 88
Quality Score
34 vs 76

Hardware

falcon3-1b-instruct qwen3.5:4b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

falcon3-1b-instruct qwen3.5:4b
Tokens/sec121.816.6
First chunk176 msN/A
TTFT176 ms369 ms
Load timeN/A1.5 s
Memory usage0.7 GB6.5 GB
Memory %2%20%

HW Fit Score Breakdown

falcon3-1b-instruct

Speed
50/50
TTFT
20/20
Memory
30/30

qwen3.5:4b

Speed
28/50
TTFT
30/20
Memory
30/30

Quality

falcon3-1b-instruct

Reasoning
7/20
Coding
1/20
Instruction
12/20
Structured
7/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Poor Multilingual: Weak

qwen3.5:4b

Reasoning
16/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

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