hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 23, 2026 · Apple M1 Pro
qwen3.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
61 vs 80
Hardware Fit
97 vs 62
Quality Score
46 vs 88
Hardware
hf.co/LiquidAI/LFM… qwen3.5-35b-a3b
MachineMacBook ProDocker Container
CPUApple M1 ProIntel Gen Intel® Core™ i9-11900H
Cores1016
RAM16 GB15 GB
GPUApple M1 ProTigerLake-H GT1 [UHD Graphics]
OSmacOS 26.6.2Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance
Performance
hf.co/LiquidAI/LFM… qwen3.5-35b-a3b
Tokens/sec31.410.6
First chunk138 ms52 ms
TTFT138 ms3.2 s
Load time3.7 s7.6 s
Memory usage6.6 GB1.1 GB
Memory %41%7%
HW Fit Score Breakdown
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
qwen3.5-35b-a3b
Speed
19/50
TTFT
13/20
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
qwen3.5-35b-a3b
Reasoning
16/20
Coding
18/20
Instruction
18/20
Structured
15/15
Math
11/15
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