lfm2.5:8b
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
qwen3.8-27b-claude-opus-reasoning-distilled
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Aug 20, 2026 · Apple M4 Max
Global Score
80 vs 80
Hardware Fit
95 vs 63
Quality Score
73 vs 87
Hardware
lfm2.5:8b qwen3.8-27b-claude…
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M4 Max
Cores1016
RAM16 GB128 GB
GPUApple M1 ProApple M4 Max
OSmacOS 26.6.2macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
lfm2.5:8b qwen3.8-27b-claude…
Tokens/sec98.524.0
First chunk167 ms20 ms
TTFT2.5 s4.5 s
Load time3.0 sN/A
Memory usage6.0 GB15.7 GB
Memory %37%12%
HW Fit Score Breakdown
lfm2.5:8b
Speed
50/50
TTFT
17/20
Memory
28/30
qwen3.8-27b-claude-opus…
Speed
27/50
TTFT
6/20
Memory
30/30
Quality
lfm2.5:8b
Reasoning
2/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.8-27b-claude-opus…
Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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