Back to leaderboard

Qwen3-Next-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · unknown

Not Rec.

Aug 18, 2026 · Intel Core™ i7-14700F

cogito:3b

OLLAMA GGUF

llama · 3.6B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
25 vs 67
Hardware Fit
71 vs 100
Quality Score
5 vs 53

Hardware

Qwen3-Next-80B:80B cogito:3b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Air
CPUIntel Core™ i7-14700FApple M4
Cores2810
RAM128 GB32 GB
GPUNVIDIA GeForce RTX 5080Apple M4
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

Qwen3-Next-80B:80B cogito:3b
Tokens/sec29.145.6
First chunk815 ms177 ms
TTFT769 ms177 ms
Load time56.9 s0.8 s
Memory usage61.7 GB7.0 GB
Memory %48%22%

HW Fit Score Breakdown

Qwen3-Next-80B:80B

Speed
29/50
TTFT
17/20
Memory
25/30

cogito:3b

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

Quality

Qwen3-Next-80B:80B

Reasoning
0/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

cogito:3b

Reasoning
6/20
Coding
8/20
Instruction
13/20
Structured
15/15
Math
2/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View Qwen3-Next-80B:80B details | View cogito:3b 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