Back to leaderboard

Qwen3-Next-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · unknown

Not Rec.

Aug 18, 2026 · Intel Core™ i7-14700F

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
25 vs 66
Hardware Fit
71 vs 87
Quality Score
5 vs 57

Hardware

Qwen3-Next-80B:80B granite-3.3-2b-ins…
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 granite-3.3-2b-ins…
Tokens/sec29.118.3
First chunk815 ms541 ms
TTFT769 ms541 ms
Load time56.9 sN/A
Memory usage61.7 GB4.7 GB
Memory %48%15%

HW Fit Score Breakdown

Qwen3-Next-80B:80B

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

granite-3.3-2b-instruct

Speed
37/50
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

granite-3.3-2b-instruct

Reasoning
10/20
Coding
10/20
Instruction
14/20
Structured
14/15
Math
2/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View Qwen3-Next-80B:80B details | View granite-3.3-2b-ins… 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