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

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

Global Score
51 vs 92
Hardware Fit
31 vs 95
Quality Score
60 vs 90

Hardware

llama3.3:70b-instr… qwen/qwen3-vl-30b
MachineDell Inc. Precision Tower 7910ASUS
CPUIntel Xeon® E5-2637 v3AMD Ryzen 5 5500
Cores1612
RAM96 GB31 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Navi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 10 Pro 10.0.19045Nobara Linux 43
Archx64x64
Power Modebalancedperformance

Performance

llama3.3:70b-instr… qwen/qwen3-vl-30b
Tokens/sec1.724.8
First chunk5553 ms11 ms
TTFT5.6 s735 ms
Load time0.4 s11.7 s
Memory usage50.3 GB0.6 GB
Memory %53%2%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

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

qwen/qwen3-vl-30b

Speed
45/50
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

qwen/qwen3-vl-30b

Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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