Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

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

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Good

Aug 18, 2026 · Intel Xeon® E5-2637 v3

Global Score
81 vs 78
Hardware Fit
96 vs 51
Quality Score
75 vs 89

Hardware

qwen3:8b qwen3-next:80b-a3b…
MachineASUSDell Inc. Precision Tower 7910
CPUIntel Core™ i5-14600KFIntel Xeon® E5-2637 v3
Cores2016
RAM32 GB96 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modebalancedbalanced

Performance

qwen3:8b qwen3-next:80b-a3b…
Tokens/sec109.18.7
First chunk190 ms1251 ms
TTFT190 ms1.3 s
Load time4.3 s61.6 s
Memory usage5.6 GB48.3 GB
Memory %18%50%

HW Fit Score Breakdown

qwen3:8b

Speed
50/50
TTFT
20/20
Memory
26/30

qwen3-next:80b-a3b-inst…

Speed
9/50
TTFT
17/20
Memory
25/30

Quality

qwen3:8b

Reasoning
15/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3-next:80b-a3b-inst…

Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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