llama-3.2-1b-instruct
LM-STUDIO GGUFllama · 1B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 23, 2026 · Apple M1 Pro
Global Score
50 vs 61
Hardware Fit
79 vs 97
Quality Score
37 vs 46
Hardware
llama-3.2-1b-instr… hf.co/LiquidAI/LFM…
MachineLENOVO 20BUS00700MacBook Pro
CPUIntel Core™ i5-5300UApple M1 Pro
Cores410
RAM16 GB16 GB
GPUIntel(R) HD Graphics 5500Apple M1 Pro
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
llama-3.2-1b-instr… hf.co/LiquidAI/LFM…
Tokens/sec9.931.4
First chunk1668 ms138 ms
TTFT1.7 s138 ms
Load timeN/A3.7 s
Memory usage0.8 GB6.6 GB
Memory %5%41%
HW Fit Score Breakdown
llama-3.2-1b-instruct
Speed
32/50
TTFT
20/20
Memory
27/30
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
llama-3.2-1b-instruct
Reasoning
4/20
Coding
3/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong
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
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