Back to leaderboard

Qwen3-Next-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · unknown

Not Rec.

Aug 18, 2026 · Intel Core™ i7-14700F

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Good

Mar 5, 2026 · Apple M1 Max

Global Score
25 vs 62
Hardware Fit
71 vs 100
Quality Score
5 vs 46

Hardware

Qwen3-Next-80B:80B qwen3.5:0.8b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M1 Max
Cores2810
RAM128 GB32 GB
GPUNVIDIA GeForce RTX 5080Apple M1 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

Qwen3-Next-80B:80B qwen3.5:0.8b
Tokens/sec29.167.6
First chunk815 ms209 ms
TTFT769 ms209 ms
Load time56.9 s1.9 s
Memory usage61.7 GB2.6 GB
Memory %48%8%

HW Fit Score Breakdown

Qwen3-Next-80B:80B

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

qwen3.5:0.8b

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

qwen3.5:0.8b

Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View Qwen3-Next-80B:80B details | View qwen3.5:0.8b 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