falcon-h1-tiny-90m-instruct
LM-STUDIO GGUFfalcon-h1 · 90M · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
Global Score
43 vs 89
Hardware Fit
99 vs 97
Quality Score
19 vs 86
Hardware
falcon-h1-tiny-90m… qwen3.6:35b-mlx
MachineLENOVO 20BUS00700MacBook Pro
CPUIntel Core™ i5-5300UApple M5 Max
Cores418
RAM16 GB48 GB
GPUIntel(R) HD Graphics 5500Apple M5 Max
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
falcon-h1-tiny-90m… qwen3.6:35b-mlx
Tokens/sec67.8129.4
First chunk762 ms49 ms
TTFT762 ms49 ms
Load timeN/A0.0 s
Memory usage0.1 GB20.5 GB
Memory %0%43%
HW Fit Score Breakdown
falcon-h1-tiny-90m-inst…
Speed
50/50
TTFT
20/20
Memory
29/30
qwen3.6:35b-mlx
Speed
50/50
TTFT
20/20
Memory
27/30
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
qwen3.6:35b-mlx
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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