lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
Global Score
73 vs 66
Hardware Fit
93 vs 91
Quality Score
65 vs 55
Hardware
lfm2.5:latest qwen3.8-27b-mlx
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M5 Max
Cores818
RAM23 GB64 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M5 Max
OSFedora Linux 44macOS 27.0
Archx64arm64
Power Modeperformancebalanced
Performance
lfm2.5:latest qwen3.8-27b-mlx
Tokens/sec18.333.2
First chunk981 ms7 ms
TTFT981 ms311 ms
Load time8.0 sN/A
Memory usage4.9 GB0.5 GB
Memory %21%1%
HW Fit Score Breakdown
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
Quality
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
qwen3.8-27b-mlx
Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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