hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 26, 2026 · Apple M1 Pro
qwen3-vl:30b
OLLAMA GGUFqwen3vlmoe · 31.1B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
61 vs 80
Hardware Fit
97 vs 98
Quality Score
46 vs 72
Hardware
hf.co/LiquidAI/LFM… qwen3-vl:30b
MachineMacBook ProASUS
CPUApple M1 ProIntel Core™ Ultra 9 285K
Cores1024
RAM16 GB47 GB
GPUApple M1 ProNVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
hf.co/LiquidAI/LFM… qwen3-vl:30b
Tokens/sec31.3208.9
First chunk131 ms102 ms
TTFT131 ms684 ms
Load time4.2 s0.1 s
Memory usage6.6 GB22.0 GB
Memory %41%47%
HW Fit Score Breakdown
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
qwen3-vl:30b
Speed
50/50
TTFT
20/20
Memory
28/30
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
qwen3-vl:30b
Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak 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