liquid/lfm2-24b-a2b
LM-STUDIO GGUFlfm2moe · 24B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
Global Score
87 vs 89
Hardware Fit
100 vs 97
Quality Score
82 vs 86
Hardware
liquid/lfm2-24b-a2b qwen3.6:35b-mlx
MachineGMKtec EVO-X3MacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M5 Max
Cores3218
RAM120 GB48 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M5 Max
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
liquid/lfm2-24b-a2b qwen3.6:35b-mlx
Tokens/sec80.9129.4
First chunk7 ms49 ms
TTFT222 ms49 ms
Load time26.6 s0.0 s
Memory usage32.1 GB20.5 GB
Memory %27%43%
HW Fit Score Breakdown
liquid/lfm2-24b-a2b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.6:35b-mlx
Speed
50/50
TTFT
20/20
Memory
27/30
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
qwen3.6:35b-mlx
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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