lfm2:24b
OLLAMA GGUFlfm2moe · 23.8B · Q4_K_M
Mar 7, 2026 · AMD RYZEN AI MAX+ 395
vicuna:13b
OLLAMA GGUFllama · 13B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
88 vs 59
Hardware Fit
100 vs 84
Quality Score
83 vs 48
Hardware
lfm2:24b vicuna:13b
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPURadeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
lfm2:24b vicuna:13b
Tokens/sec85.313.4
First chunk123 msN/A
TTFT123 ms438 ms
Load time2.9 s0.6 s
Memory usage14.3 GB10.3 GB
Memory %12%32%
HW Fit Score Breakdown
lfm2:24b
Speed
50/50
TTFT
20/20
Memory
30/30
vicuna:13b
Speed
24/50
TTFT
30/20
Memory
30/30
Quality
lfm2:24b
Reasoning
14/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
vicuna:13b
Reasoning
7/20
Coding
5/20
Instruction
12/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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