lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 20, 2026 · AMD RYZEN AI MAX+ 395
qwen3.5-27b-claude-4.6-opus-distilled-mlx
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Mar 10, 2026 · Apple M4
Global Score
79 vs 34
Hardware Fit
100 vs 21
Quality Score
70 vs 39
Hardware
lfm2.5:latest qwen3.5-27b-claude…
MachineAZW GTR ProMac mini
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB24 GB
GPURadeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
lfm2.5:latest qwen3.5-27b-claude…
Tokens/sec134.46.1
First chunk226 ms7 ms
TTFT226 ms22.9 s
Load time1.8 sN/A
Memory usage6.9 GB19.8 GB
Memory %6%82%
HW Fit Score Breakdown
lfm2.5:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5-27b-claude-4.6-…
Speed
12/50
TTFT
0/20
Memory
9/30
Quality
lfm2.5:latest
Reasoning
2/20
Coding
11/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5-27b-claude-4.6-…
Reasoning
1/20
Coding
14/20
Instruction
5/20
Structured
8/15
Math
4/15
Multilingual
7/10
Reasoning: Poor Coding: Adequate Instruction Following: Weak Structured Output: Adequate Math: Poor Multilingual: Adequate
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