hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 23, 2026 · Apple M1 Pro
qwen/qwen3-vl-30b
LM-STUDIO GGUFqwen3vlmoe · 30B · Q4_K_M
Apr 24, 2026 · AMD Ryzen 5 5500
Global Score
61 vs 92
Hardware Fit
97 vs 95
Quality Score
46 vs 90
Hardware
hf.co/LiquidAI/LFM… qwen/qwen3-vl-30b
MachineMacBook ProASUS
CPUApple M1 ProAMD Ryzen 5 5500
Cores1012
RAM16 GB31 GB
GPUApple M1 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.6.2Nobara Linux 43
Archarm64x64
Power Modebalancedperformance
Performance
hf.co/LiquidAI/LFM… qwen/qwen3-vl-30b
Tokens/sec31.424.8
First chunk138 ms11 ms
TTFT138 ms735 ms
Load time3.7 s11.7 s
Memory usage6.6 GB0.6 GB
Memory %41%2%
HW Fit Score Breakdown
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
qwen/qwen3-vl-30b
Speed
45/50
TTFT
20/20
Memory
30/30
Quality
hf.co/LiquidAI/LFM2.5-2…
Reasoning
14/20
Coding
13/20
Instruction
3/20
Structured
0/15
Math
14/15
Multilingual
2/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
qwen/qwen3-vl-30b
Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong 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