hf.co/Edge-Quant/Nanbeige4.1-3B-Q8_0-GGUF:Q8_0
OLLAMA GGUFllama · 3.93B · unknown
Aug 22, 2026 · Apple M1 Pro
lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
Global Score
52 vs 73
Hardware Fit
75 vs 93
Quality Score
42 vs 65
Hardware
hf.co/Edge-Quant/N… lfm2.5:latest
MachineMacBook ProLENOVO 20L7CTO1WW
CPUApple M1 ProIntel Core™ i5-8350U
Cores108
RAM16 GB23 GB
GPUApple M1 ProKaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.6.2Fedora Linux 44
Archarm64x64
Power Modebalancedperformance
Performance
hf.co/Edge-Quant/N… lfm2.5:latest
Tokens/sec43.518.3
First chunk225 ms981 ms
TTFT30.0 s981 ms
Load time2.7 s8.0 s
Memory usage8.2 GB4.9 GB
Memory %51%21%
HW Fit Score Breakdown
hf.co/Edge-Quant/Nanbei…
Speed
50/50
TTFT
0/20
Memory
25/30
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
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
lfm2.5:latest
Reasoning
2/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate 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