Back to leaderboard

qwen3-next-80b-t48:latest

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
70 vs 65
Hardware Fit
39 vs 88
Quality Score
83 vs 55

Hardware

qwen3-next-80b-t48… qwen3.5-2b-mlx
MachineDell Inc. PowerEdge R820Mac mini
CPUIntel Xeon® E5-4620 0Apple M4 Pro
Cores6414
RAM256 GB64 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterApple M4 Pro
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-next-80b-t48… qwen3.5-2b-mlx
Tokens/sec3.048.9
First chunk3265 ms4208 ms
TTFT3.3 s4.2 s
Load time82.1 sN/A
Memory usage46.9 GB1.6 GB
Memory %18%3%

HW Fit Score Breakdown

qwen3-next-80b-t48:latest

Speed
3/50
TTFT
6/20
Memory
30/30

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

Quality

qwen3-next-80b-t48:latest

Reasoning
18/20
Coding
18/20
Instruction
9/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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