Back to leaderboard

qwen3-next:80b-a3b-instruct-q4_K_M

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Excellent

Aug 1, 2026 · Intel Xeon® E5-2637 v3

qwen2.5-1.5b-instruct

LM-STUDIO GGUF

qwen2 · 1.5B · Q4_K_M

Good

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score
80 vs 61
Hardware Fit
54 vs 69
Quality Score
91 vs 58

Hardware

qwen3-next:80b-a3b… qwen2.5-1.5b-instr…
MachineDell Inc. Precision Tower 7910LENOVO 20BUS00700
CPUIntel Xeon® E5-2637 v3Intel Core™ i5-5300U
Cores164
RAM96 GB16 GB
GPUNVIDIA GeForce RTX 5060 TiIntel(R) HD Graphics 5500
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-next:80b-a3b… qwen2.5-1.5b-instr…
Tokens/sec14.96.6
First chunk1808 ms2277 ms
TTFT1.8 s2.3 s
Load time95.0 sN/A
Memory usage48.0 GB0.9 GB
Memory %50%6%

HW Fit Score Breakdown

qwen3-next:80b-a3b-inst…

Speed
16/50
TTFT
13/20
Memory
25/30

qwen2.5-1.5b-instruct

Speed
23/50
TTFT
19/20
Memory
27/30

Quality

qwen3-next:80b-a3b-inst…

Reasoning
18/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen2.5-1.5b-instruct

Reasoning
9/20
Coding
9/20
Instruction
13/20
Structured
14/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak 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