hf.co/Edge-Quant/Nanbeige4.1-3B-Q8_0-GGUF:Q8_0
OLLAMA GGUFllama · 3.93B · unknown
Aug 22, 2026 · Apple M1 Pro
qwen2.5-1.5b-instruct
LM-STUDIO GGUFqwen2 · 1.5B · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
Global Score
52 vs 61
Hardware Fit
75 vs 69
Quality Score
42 vs 58
Hardware
hf.co/Edge-Quant/N… qwen2.5-1.5b-instr…
MachineMacBook ProLENOVO 20BUS00700
CPUApple M1 ProIntel Core™ i5-5300U
Cores104
RAM16 GB16 GB
GPUApple M1 ProIntel(R) HD Graphics 5500
OSmacOS 26.6.2Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
hf.co/Edge-Quant/N… qwen2.5-1.5b-instr…
Tokens/sec43.56.6
First chunk225 ms2277 ms
TTFT30.0 s2.3 s
Load time2.7 sN/A
Memory usage8.2 GB0.9 GB
Memory %51%6%
HW Fit Score Breakdown
hf.co/Edge-Quant/Nanbei…
Speed
50/50
TTFT
0/20
Memory
25/30
qwen2.5-1.5b-instruct
Speed
23/50
TTFT
19/20
Memory
27/30
Quality
hf.co/Edge-Quant/Nanbei…
Reasoning
13/20
Coding
1/20
Instruction
7/20
Structured
1/15
Math
13/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate
qwen2.5-1.5b-instruct
Reasoning
9/20
Coding
9/20
Instruction
13/20
Structured
14/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Weak 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