Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Apr 1, 2026 · Apple M4

qwen3-235b-a22b-t48-c8k:latest

OLLAMA GGUF

qwen3moe · 235.1B · Q4_K_M

Not Rec.

Aug 23, 2026 · Intel Xeon® E5-4650 v2

Global Score
82 vs 61
Hardware Fit
85 vs 31
Quality Score
81 vs 74

Hardware

openai/gpt-oss-20b qwen3-235b-a22b-t4…
MachineMac miniDell Inc. PowerEdge R820
CPUApple M4Intel Xeon® E5-4650 v2
Cores1080
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

openai/gpt-oss-20b qwen3-235b-a22b-t4…
Tokens/sec31.81.7
First chunk32 ms3351 ms
TTFT8.4 s3.4 s
Load time22.7 s0.0 s
Memory usage0.0 GB134.2 GB
Memory %0%52%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
5/20
Memory
30/30

qwen3-235b-a22b-t48-c8k…

Speed
1/50
TTFT
6/20
Memory
24/30

Quality

openai/gpt-oss-20b

Reasoning
19/20
Coding
14/20
Instruction
9/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong

qwen3-235b-a22b-t48-c8k…

Reasoning
19/20
Coding
11/20
Instruction
7/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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