lfm2:24b-a2b
OLLAMA GGUFlfm2moe · 23.8B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive
OPENAI GGUFApr 21, 2026 · Apple M2 Max
Global Score
78 vs 62
Hardware Fit
67 vs 100
Quality Score
82 vs 45
Hardware
lfm2:24b-a2b qwen3.5-35b-a3b-un…
MachineDell Inc. Inspiron 15 3530Mac Studio
CPUIntel Gen Intel® Core™ i7-1355UApple M2 Max
Cores1212
RAM31 GB96 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M2 Max
OScachyos rollingmacOS 26.1
Archx64arm64
Power Modelow-powerbalanced
Performance
lfm2:24b-a2b qwen3.5-35b-a3b-un…
Tokens/sec11.567.9
First chunk1727 ms50 ms
TTFT1.7 s75 ms
Load time6.8 s0.0 s
Memory usage13.9 GB0.0 GB
Memory %45%0%
HW Fit Score Breakdown
lfm2:24b-a2b
Speed
22/50
TTFT
19/20
Memory
26/30
qwen3.5-35b-a3b-uncenso…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
lfm2:24b-a2b
Reasoning
13/20
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
qwen3.5-35b-a3b-uncenso…
Reasoning
16/20
Coding
0/20
Instruction
12/20
Structured
0/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Poor 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