lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 20, 2026 · AMD RYZEN AI MAX+ 395
qwen3-5-4b-q4-k-m
OLLAMA GGUFllama · 4B · Q4_K_M
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
79 vs 83
Hardware Fit
100 vs 100
Quality Score
70 vs 76
Hardware
lfm2.5:latest qwen3-5-4b-q4-k-m
MachineAZW GTR ProMac Pro
CPUAMD RYZEN AI MAX+ 395Intel Core™ i5-10400
Cores3212
RAM125 GB32 GB
GPURadeon 8060SAMD Radeon RX 6700 XT
OSUbuntu 24.04.4 LTSmacOS 26.5.1
Archx64x64
Power Modelow-powerbalanced
Performance
lfm2.5:latest qwen3-5-4b-q4-k-m
Tokens/sec134.462.7
First chunk226 ms278 ms
TTFT226 ms278 ms
Load time1.8 s0.0 s
Memory usage6.9 GB0.0 GB
Memory %6%0%
HW Fit Score Breakdown
lfm2.5:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-5-4b-q4-k-m
Speed
50/50
TTFT
20/20
Memory
30/30
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
qwen3-5-4b-q4-k-m
Reasoning
14/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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