Back to leaderboard

unsloth/qwen3.5-9b@q4_k_m

LM-STUDIO GGUF

qwen35 · 9B · Q4_K_M

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 22, 2026 · Apple M1 Pro

Global Score
73 vs 66
Hardware Fit
52 vs 100
Quality Score
82 vs 52

Hardware

unsloth/qwen3.5-9b… hf.co/empero-ai/Qw…
MachineDocker ContainerMacBook Pro
CPUIntel Gen Intel® Core™ i9-11900HApple M1 Pro
Cores1610
RAM15 GB16 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M1 Pro
OSUbuntu 26.04 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced

Performance

unsloth/qwen3.5-9b… hf.co/empero-ai/Qw…
Tokens/sec6.540.2
First chunk13 ms325 ms
TTFT4.1 s325 ms
Load time10.8 s3.1 s
Memory usage2.2 GB4.7 GB
Memory %14%30%

HW Fit Score Breakdown

unsloth/qwen3.5-9b@q4_k_m

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

hf.co/empero-ai/Qwen3.8…

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

Quality

unsloth/qwen3.5-9b@q4_k_m

Reasoning
15/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

hf.co/empero-ai/Qwen3.8…

Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
View unsloth/qwen3.5-9b… details | View hf.co/empero-ai/Qw… 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