llama3.3:70b
OLLAMA GGUFllama · 70.6B · Q4_K_M
Jun 26, 2026 · Cortex-X925
lfm2-24b-a2b
LM-STUDIO GGUFMar 6, 2026 · Apple M4 Pro
Global Score
73 vs 78
Hardware Fit
51 vs 100
Quality Score
83 vs 68
Hardware
llama3.3:70b lfm2-24b-a2b
MachineNVIDIA NVIDIA_DGX_SparkMac mini
CPUCortex-X925Apple M4 Pro
Cores2014
RAM122 GB64 GB
GPUDevice 2e12Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.4
Archarm64arm64
Power Modeperformancebalanced
Performance
llama3.3:70b lfm2-24b-a2b
Tokens/sec4.6105.9
First chunk560 ms252 ms
TTFT560 ms252 ms
Load time13.8 sN/A
Memory usage49.5 GB0.1 GB
Memory %41%0%
HW Fit Score Breakdown
llama3.3:70b
Speed
4/50
TTFT
20/20
Memory
27/30
lfm2-24b-a2b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
llama3.3:70b
Reasoning
17/20
Coding
18/20
Instruction
12/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
lfm2-24b-a2b
Reasoning
12/20
Coding
14/20
Instruction
12/20
Structured
13/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate 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