Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

gpt-oss-safeguard-20b-mlx

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 12, 2026 · Apple M4

Global Score
81 vs 87
Hardware Fit
95 vs 82
Quality Score
75 vs 89

Hardware

qwen3:8b gpt-oss-safeguard-…
MachineASUSMac mini
CPUIntel Core™ i5-14600KFApple M4
Cores2010
RAM32 GB24 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERApple M4
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3:8b gpt-oss-safeguard-…
Tokens/sec108.341.4
First chunk169 ms8 ms
TTFT169 ms3.6 s
Load time1.7 sN/A
Memory usage5.6 GB14.5 GB
Memory %18%61%

HW Fit Score Breakdown

qwen3:8b

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

gpt-oss-safeguard-20b-mlx

Speed
50/50
TTFT
12/20
Memory
20/30

Quality

qwen3:8b

Reasoning
15/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

gpt-oss-safeguard-20b-mlx

Reasoning
19/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong 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