Back to leaderboard

hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ2_XXS

OLLAMA GGUF

qwen35 · 27.3B · unknown

Not Rec.

Aug 22, 2026 · Apple M1 Pro

gpt-oss-safeguard-20b-mlx

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 12, 2026 · Apple M4

Global Score
31 vs 87
Hardware Fit
37 vs 82
Quality Score
28 vs 89

Hardware

hf.co/unsloth/Qwen… gpt-oss-safeguard-…
MachineMacBook ProMac mini
CPUApple M1 ProApple M4
Cores1010
RAM16 GB24 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/unsloth/Qwen… gpt-oss-safeguard-…
Tokens/sec5.441.4
First chunk5076 ms8 ms
TTFT5.1 s3.6 s
Load time0.3 sN/A
Memory usage11.6 GB14.5 GB
Memory %72%61%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

Speed
13/50
TTFT
10/20
Memory
14/30

gpt-oss-safeguard-20b-mlx

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

Quality

hf.co/unsloth/Qwen3.8-2…

Reasoning
9/20
Coding
2/20
Instruction
1/20
Structured
1/15
Math
9/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Adequate

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
View hf.co/unsloth/Qwen… details | View gpt-oss-safeguard-… details

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