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

google/gemma-4-12b-qat

LM-STUDIO GGUF

gemma4 · 12B · Q4_0

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
51 vs 92
Hardware Fit
31 vs 100
Quality Score
60 vs 89

Hardware

llama3.3:70b-instr… google/gemma-4-12b…
MachineDell Inc. Precision Tower 7910Micro-Star International Co., Ltd. MS-7E51
CPUIntel Xeon® E5-2637 v3AMD Ryzen 7 9700X 8-Core Processor
Cores1616
RAM96 GB31 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

llama3.3:70b-instr… google/gemma-4-12b…
Tokens/sec1.790.7
First chunk5553 ms26 ms
TTFT5.6 s127 ms
Load time0.4 sN/A
Memory usage50.3 GB6.7 GB
Memory %53%21%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

Speed
2/50
TTFT
5/20
Memory
24/30

google/gemma-4-12b-qat

Speed
50/50
TTFT
20/20
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

google/gemma-4-12b-qat

Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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