Back to leaderboard

unsloth/gemma-4-26b-a4b-it@q4_k_m

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_M

Excellent

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

qwen3-30b-a3b-t16-c32k-instruct:latest

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 18, 2026 · Intel Xeon® E5-2637 v3

Global Score
83 vs 94
Hardware Fit
58 vs 100
Quality Score
93 vs 91

Hardware

unsloth/gemma-4-26… qwen3-30b-a3b-t16-…
MachineDocker ContainerDell Inc. Precision Tower 7910
CPUIntel Gen Intel® Core™ i9-11900HIntel Xeon® E5-2637 v3
Cores1616
RAM15 GB96 GB
GPUTigerLake-H GT1 [UHD Graphics]NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSUbuntu 26.04 LTSMicrosoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modeperformancebalanced

Performance

unsloth/gemma-4-26… qwen3-30b-a3b-t16-…
Tokens/sec9.4116.0
First chunk42 ms575 ms
TTFT4.1 s575 ms
Load time44.3 s10.2 s
Memory usage0.2 GB21.0 GB
Memory %1%22%

HW Fit Score Breakdown

unsloth/gemma-4-26b-a4b…

Speed
17/50
TTFT
11/20
Memory
30/30

qwen3-30b-a3b-t16-c32k-…

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

Quality

unsloth/gemma-4-26b-a4b…

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

qwen3-30b-a3b-t16-c32k-…

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
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