Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

falcon-h1-0.5b-instruct

LM-STUDIO GGUF

falcon-h1 · 0.5B · Q4_K_M

Marginal

Mar 8, 2026 · Intel Core™ i5-5300U

Global Score
53 vs 57
Hardware Fit
72 vs 91
Quality Score
45 vs 42

Hardware

qwen3.5:9b falcon-h1-0.5b-ins…
MachineMacBook ProLENOVO 20BUS00700
CPUApple M1 MaxIntel Core™ i5-5300U
Cores104
RAM32 GB16 GB
GPUApple M1 MaxIntel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:9b falcon-h1-0.5b-ins…
Tokens/sec18.616.3
First chunk403 ms2987 ms
TTFT10.2 s3.0 s
Load time4.3 sN/A
Memory usage9.1 GB0.3 GB
Memory %28%2%

HW Fit Score Breakdown

qwen3.5:9b

Speed
38/50
TTFT
4/20
Memory
30/30

falcon-h1-0.5b-instruct

Speed
48/50
TTFT
16/20
Memory
27/30

Quality

qwen3.5:9b

Reasoning
12/20
Coding
3/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong

falcon-h1-0.5b-instruct

Reasoning
8/20
Coding
7/20
Instruction
12/20
Structured
10/15
Math
4/15
Multilingual
1/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Poor

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