llama3.3:70b-instruct-q4_K_M
OLLAMA GGUFllama · 70.6B · Q4_K_M
Aug 20, 2026 · Intel Xeon® E5-2637 v3
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
51 vs 88
Hardware Fit
31 vs 86
Quality Score
60 vs 89
Hardware
llama3.3:70b-instr… gemma4:12b-it-qat
MachineDell Inc. Precision Tower 7910Mac mini
CPUIntel Xeon® E5-2637 v3Apple M4 Pro
Cores1612
RAM96 GB24 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Apple M4 Pro
OSMicrosoft Windows 10 Pro 10.0.19045macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced
Performance
llama3.3:70b-instr… gemma4:12b-it-qat
Tokens/sec1.730.0
First chunk5553 ms686 ms
TTFT5.6 s7.1 s
Load time0.4 s5.4 s
Memory usage50.3 GB7.1 GB
Memory %53%30%
HW Fit Score Breakdown
llama3.3:70b-instruct-q…
Speed
2/50
TTFT
5/20
Memory
24/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
llama3.3:70b-instruct-q…
Reasoning
17/20
Coding
6/20
Instruction
6/20
Structured
11/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Weak Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Strong
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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