qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive
OPENAI GGUFApr 21, 2026 · Apple M2 Max
falcon-h1-tiny-90m-instruct
LM-STUDIO GGUFfalcon-h1 · 90M · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
Global Score
62 vs 43
Hardware Fit
100 vs 99
Quality Score
45 vs 19
Hardware
qwen3.5-35b-a3b-un… falcon-h1-tiny-90m…
MachineMac StudioLENOVO 20BUS00700
CPUApple M2 MaxIntel Core™ i5-5300U
Cores124
RAM96 GB16 GB
GPUApple M2 MaxIntel(R) HD Graphics 5500
OSmacOS 26.1Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.5-35b-a3b-un… falcon-h1-tiny-90m…
Tokens/sec67.967.8
First chunk50 ms762 ms
TTFT75 ms762 ms
Load time0.0 sN/A
Memory usage0.0 GB0.1 GB
Memory %0%0%
HW Fit Score Breakdown
qwen3.5-35b-a3b-uncenso…
Speed
50/50
TTFT
20/20
Memory
30/30
falcon-h1-tiny-90m-inst…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwen3.5-35b-a3b-uncenso…
Reasoning
16/20
Coding
0/20
Instruction
12/20
Structured
0/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Poor Math: Adequate Multilingual: Strong
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
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