Back to leaderboard

llama3.3:70b-instruct-q4_K_M

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Aug 20, 2026 · Intel Xeon® E5-2637 v3

gemma4:12b-it-qat

OLLAMA GGUF

gemma4 · 11.9B · Q4_0

Excellent

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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest