Back to leaderboard

unsloth/gemma-4-e4b-it@q4_k_m

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

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

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

Global Score
79 vs 81
Hardware Fit
68 vs 100
Quality Score
84 vs 73

Hardware

unsloth/gemma-4-e4… llama-3.1-8b-instr…
MachineDocker ContainerASUS
CPUIntel Gen Intel® Core™ i9-11900HAMD Ryzen 5 5500
Cores1612
RAM15 GB31 GB
GPUTigerLake-H GT1 [UHD Graphics]Navi 44 [Radeon RX 9060 XT]
OSUbuntu 26.04 LTSNobara Linux 43
Archx64x64
Power Modeperformanceperformance

Performance

unsloth/gemma-4-e4… llama-3.1-8b-instr…
Tokens/sec10.835.6
First chunk32 ms52 ms
TTFT2.0 s256 ms
Load time9.2 sN/A
Memory usage0.8 GB8.6 GB
Memory %5%28%

HW Fit Score Breakdown

unsloth/gemma-4-e4b-it@…

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

llama-3.1-8b-instruct

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

Quality

unsloth/gemma-4-e4b-it@…

Reasoning
15/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

llama-3.1-8b-instruct

Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View unsloth/gemma-4-e4… details | View llama-3.1-8b-instr… 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