falcon-h1-tiny-90m-instruct
LM-STUDIO GGUFfalcon-h1 · 90M · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
cogito:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
43 vs 77
Hardware Fit
99 vs 92
Quality Score
19 vs 70
Hardware
falcon-h1-tiny-90m… cogito:8b
MachineLENOVO 20BUS00700MacBook Air
CPUIntel Core™ i5-5300UApple M4
Cores410
RAM16 GB32 GB
GPUIntel(R) HD Graphics 5500Apple M4
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
falcon-h1-tiny-90m… cogito:8b
Tokens/sec67.821.0
First chunk762 ms312 ms
TTFT762 ms312 ms
Load timeN/A0.8 s
Memory usage0.1 GB10.4 GB
Memory %0%33%
HW Fit Score Breakdown
falcon-h1-tiny-90m-inst…
Speed
50/50
TTFT
20/20
Memory
29/30
cogito:8b
Speed
42/50
TTFT
20/20
Memory
30/30
Quality
falcon-h1-tiny-90m-inst…
Reasoning
5/20
Coding
0/20
Instruction
7/20
Structured
3/15
Math
2/15
Multilingual
2/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
cogito:8b
Reasoning
14/20
Coding
13/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest