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

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
73 vs 62
Hardware Fit
52 vs 77
Quality Score
82 vs 55

Hardware

unsloth/qwen3.5-9b… google/gemma-4-e4b
MachineDocker ContainerLENOVO 82JQ
CPUIntel Gen Intel® Core™ i9-11900HAMD Ryzen 7 5800H
Cores1616
RAM15 GB16 GB
GPUTigerLake-H GT1 [UHD Graphics]NVIDIA GeForce RTX 3060 Laptop GPU
OSUbuntu 26.04 LTSMicrosoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modeperformancebalanced

Performance

unsloth/qwen3.5-9b… google/gemma-4-e4b
Tokens/sec6.527.6
First chunk13 ms23 ms
TTFT4.1 s480 ms
Load time10.8 sN/A
Memory usage2.2 GB13.2 GB
Memory %14%83%

HW Fit Score Breakdown

unsloth/qwen3.5-9b@q4_k_m

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

google/gemma-4-e4b

Speed
48/50
TTFT
20/20
Memory
9/30

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

google/gemma-4-e4b

Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
View unsloth/qwen3.5-9b… details | View google/gemma-4-e4b 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