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

lmstudio-community/gemma-4-e2b-it

LM-STUDIO GGUF

gemma4 · Q8_0

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
51 vs 77
Hardware Fit
31 vs 75
Quality Score
60 vs 78

Hardware

llama3.3:70b-instr… lmstudio-community…
MachineDell Inc. Precision Tower 7910Docker Container
CPUIntel Xeon® E5-2637 v3Intel Gen Intel® Core™ i9-11900H
Cores1616
RAM96 GB15 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060TigerLake-H GT1 [UHD Graphics]
OSMicrosoft Windows 10 Pro 10.0.19045Ubuntu 26.04 LTS
Archx64x64
Power Modebalancedperformance

Performance

llama3.3:70b-instr… lmstudio-community…
Tokens/sec1.713.3
First chunk5553 ms18 ms
TTFT5.6 s1.4 s
Load time0.4 s8.1 s
Memory usage50.3 GB0.0 GB
Memory %53%0%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

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

lmstudio-community/gemm…

Speed
25/50
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

lmstudio-community/gemm…

Reasoning
12/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate 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