Back to leaderboard

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

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Good

Aug 20, 2026 · Intel Xeon® E5-2637 v3

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · Intel Core™ Ultra X7 358H

Global Score
78 vs 86
Hardware Fit
49 vs 78
Quality Score
91 vs 89

Hardware

qwen3-next:80b-a3b… Kimi-48B:48B
MachineDell Inc. Precision Tower 7910GMKtec NucBox EVO-T2S
CPUIntel Xeon® E5-2637 v3Intel Core™ Ultra X7 358H
Cores1616
RAM96 GB64 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Intel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-next:80b-a3b… Kimi-48B:48B
Tokens/sec8.722.8
First chunk1524 ms721 ms
TTFT1.5 s721 ms
Load time63.9 s23.0 s
Memory usage48.3 GB25.5 GB
Memory %50%40%

HW Fit Score Breakdown

qwen3-next:80b-a3b-inst…

Speed
9/50
TTFT
15/20
Memory
25/30

Kimi-48B:48B

Speed
31/50
TTFT
20/20
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

Kimi-48B:48B

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
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