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

lfm2.5:latest

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Good

Jun 20, 2026 · AMD RYZEN AI MAX+ 395

Global Score
51 vs 79
Hardware Fit
31 vs 100
Quality Score
60 vs 70

Hardware

llama3.3:70b-instr… lfm2.5:latest
MachineDell Inc. Precision Tower 7910AZW GTR Pro
CPUIntel Xeon® E5-2637 v3AMD RYZEN AI MAX+ 395
Cores1632
RAM96 GB125 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Radeon 8060S
OSMicrosoft Windows 10 Pro 10.0.19045Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power

Performance

llama3.3:70b-instr… lfm2.5:latest
Tokens/sec1.7134.4
First chunk5553 ms226 ms
TTFT5.6 s226 ms
Load time0.4 s1.8 s
Memory usage50.3 GB6.9 GB
Memory %53%6%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

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

lfm2.5:latest

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

lfm2.5:latest

Reasoning
2/20
Coding
11/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Strong 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