Back to leaderboard

hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_S

OLLAMA GGUF

qwen35 · 27.3B · unknown

Marginal

Aug 25, 2026 · Apple M1 Pro

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Good

Mar 7, 2026 · AMD Ryzen 5 5500

Global Score
46 vs 71
Hardware Fit
50 vs 56
Quality Score
44 vs 78

Hardware

hf.co/unsloth/Qwen… qwen3.5:9b
MachineMacBook ProSystem manufacturer
CPUApple M1 ProAMD Ryzen 5 5500
Cores1012
RAM16 GB16 GB
GPUApple M1 ProNVIDIA GeForce RTX 3060
OSmacOS 26.6.2Microsoft Windows 11 IoT Enterprise LTSC 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

hf.co/unsloth/Qwen… qwen3.5:9b
Tokens/sec6.05.3
First chunk2377 ms1624 ms
TTFT2.2 s1.6 s
Load time6.8 s4.0 s
Memory usage10.6 GB7.9 GB
Memory %66%50%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

Speed
15/50
TTFT
18/20
Memory
17/30

qwen3.5:9b

Speed
11/50
TTFT
20/20
Memory
25/30

Quality

hf.co/unsloth/Qwen3.8-2…

Reasoning
8/20
Coding
5/20
Instruction
10/20
Structured
11/15
Math
3/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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