Back to leaderboard

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Mar 19, 2026 · Apple M4

qwen3-next-80b-t48:latest

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

Global Score
87 vs 70
Hardware Fit
79 vs 39
Quality Score
90 vs 83

Hardware

gpt-oss:20b qwen3-next-80b-t48…
MachineMac miniDell Inc. PowerEdge R820
CPUApple M4Intel Xeon® E5-4620 0
Cores1064
RAM24 GB256 GB
GPUApple M4Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSmacOS 26.3Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

gpt-oss:20b qwen3-next-80b-t48…
Tokens/sec26.43.0
First chunk505 ms3265 ms
TTFT6.7 s3.3 s
Load time10.5 s82.1 s
Memory usage13.1 GB46.9 GB
Memory %55%18%

HW Fit Score Breakdown

gpt-oss:20b

Speed
50/50
TTFT
6/20
Memory
23/30

qwen3-next-80b-t48:latest

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

Quality

gpt-oss:20b

Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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

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