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

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 24, 2026 · Intel Core™ Ultra X7 358H

Global Score
31 vs 86
Hardware Fit
37 vs 78
Quality Score
28 vs 89

Hardware

hf.co/unsloth/Qwen… Kimi-48B:48B
MachineMacBook ProGMKtec NucBox EVO-T2S
CPUApple M1 ProIntel Core™ Ultra X7 358H
Cores1016
RAM16 GB64 GB
GPUApple M1 ProIntel(R) Arc(TM) B390 GPU
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

hf.co/unsloth/Qwen… Kimi-48B:48B
Tokens/sec5.423.1
First chunk5076 ms752 ms
TTFT5.1 s752 ms
Load time0.3 s22.2 s
Memory usage11.6 GB25.5 GB
Memory %72%40%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

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

Kimi-48B:48B

Speed
31/50
TTFT
20/20
Memory
27/30

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

Kimi-48B:48B

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong 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