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

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Good

Jun 18, 2026 · AMD Ryzen 5 5500U

Global Score
51 vs 78
Hardware Fit
31 vs 54
Quality Score
60 vs 88

Hardware

llama3.3:70b-instr… qwen3-coder:30b-a3…
MachineDell Inc. Precision Tower 7910HP HP Pavilion Laptop 15-eh1xxx
CPUIntel Xeon® E5-2637 v3AMD Ryzen 5 5500U
Cores1612
RAM96 GB63 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060AMD Radeon(TM) Graphics
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 10 Enterprise LTSC 10.0.19044
Archx64x64
Power Modebalancedbalanced

Performance

llama3.3:70b-instr… qwen3-coder:30b-a3…
Tokens/sec1.78.0
First chunk5553 ms1468 ms
TTFT5.6 s1.5 s
Load time0.4 s114.5 s
Memory usage50.3 GB33.5 GB
Memory %53%53%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

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

qwen3-coder:30b-a3b-q8_0

Speed
11/50
TTFT
19/20
Memory
24/30

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

qwen3-coder:30b-a3b-q8_0

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View llama3.3:70b-instr… details | View qwen3-coder:30b-a3… details

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