liquid/lfm2-24b-a2b
LM-STUDIO GGUFlfm2moe · 24B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Apr 21, 2026 · Apple M2 Max
Global Score
87 vs 71
Hardware Fit
100 vs 92
Quality Score
82 vs 62
Hardware
liquid/lfm2-24b-a2b qwen3.5-35b-a3b-un…
MachineGMKtec EVO-X3Mac Studio
CPUAMD RYZEN AI MAX+ 395Apple M2 Max
Cores3212
RAM120 GB96 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M2 Max
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.1
Archx64arm64
Power Modebalancedbalanced
Performance
liquid/lfm2-24b-a2b qwen3.5-35b-a3b-un…
Tokens/sec80.959.8
First chunk7 ms5 ms
TTFT222 ms2.4 s
Load time26.6 s8.5 s
Memory usage32.1 GB0.4 GB
Memory %27%0%
HW Fit Score Breakdown
liquid/lfm2-24b-a2b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5-35b-a3b-uncenso…
Speed
50/50
TTFT
12/20
Memory
30/30
Quality
liquid/lfm2-24b-a2b
Reasoning
15/20
Coding
17/20
Instruction
15/20
Structured
14/15
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
18/20
Coding
8/20
Instruction
13/20
Structured
6/15
Math
12/15
Multilingual
5/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong 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