Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

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

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Aug 23, 2026 · Intel Xeon® E5-4650 v2

Global Score
53 vs 74
Hardware Fit
82 vs 42
Quality Score
41 vs 87

Hardware

qwen3.5:4b-mlx qwen3-next:80b-a3b…
MachineMac miniDell Inc. PowerEdge R820
CPUApple M2Intel Xeon® E5-4650 v2
Cores880
RAM8 GB256 GB
GPUApple M2Microsoft Basic Display Adapter
OSmacOS 26.5.2Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx qwen3-next:80b-a3b…
Tokens/sec24.73.9
First chunk302 ms2089 ms
TTFT7.4 s2.1 s
Load time3.2 s73.3 s
Memory usage3.8 GB46.9 GB
Memory %47%18%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

qwen3-next:80b-a3b-inst…

Speed
3/50
TTFT
9/20
Memory
30/30

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

qwen3-next:80b-a3b-inst…

Reasoning
18/20
Coding
19/20
Instruction
12/20
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