Back to leaderboard

lfm2.5:latest

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Good

Jun 20, 2026 · AMD RYZEN AI MAX+ 395

qwen3-235b-a22b-t48-c8k:latest

OLLAMA GGUF

qwen3moe · 235.1B · Q4_K_M

Not Rec.

Aug 2, 2026 · Intel Xeon® E5-4620 0

Global Score
79 vs 43
Hardware Fit
100 vs 28
Quality Score
70 vs 49

Hardware

lfm2.5:latest qwen3-235b-a22b-t4…
MachineAZW GTR ProDell Inc. PowerEdge R820
CPUAMD RYZEN AI MAX+ 395Intel Xeon® E5-4620 0
Cores3264
RAM125 GB256 GB
GPURadeon 8060SMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSUbuntu 24.04.4 LTSMicrosoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modelow-powerbalanced

Performance

lfm2.5:latest qwen3-235b-a22b-t4…
Tokens/sec134.40.7
First chunk226 ms6361 ms
TTFT226 ms6.4 s
Load time1.8 s0.9 s
Memory usage6.9 GB134.2 GB
Memory %6%52%

HW Fit Score Breakdown

lfm2.5:latest

Speed
50/50
TTFT
20/20
Memory
30/30

qwen3-235b-a22b-t48-c8k…

Speed
1/50
TTFT
3/20
Memory
24/30

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

qwen3-235b-a22b-t48-c8k…

Reasoning
19/20
Coding
2/20
Instruction
4/20
Structured
2/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest