Back to leaderboard

unsloth/gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_XL

Excellent

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

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 18, 2026 · Apple M4 Max

Global Score
85 vs 81
Hardware Fit
65 vs 68
Quality Score
93 vs 87

Hardware

unsloth/gemma-4-26… qwen/qwen3.8-27b
MachineDocker ContainerMacBook Pro
CPUIntel Gen Intel® Core™ i9-11900HApple M4 Max
Cores1616
RAM15 GB128 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M4 Max
OSUbuntu 26.04 LTSmacOS 26.5.2
Archx64arm64
Power Modeperformancebalanced

Performance

unsloth/gemma-4-26… qwen/qwen3.8-27b
Tokens/sec11.916.4
First chunk17 ms5 ms
TTFT3.3 s742 ms
Load time69.8 sN/A
Memory usage0.5 GB38.5 GB
Memory %3%30%

HW Fit Score Breakdown

unsloth/gemma-4-26b-a4b…

Speed
22/50
TTFT
13/20
Memory
30/30

qwen/qwen3.8-27b

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

Quality

unsloth/gemma-4-26b-a4b…

Reasoning
19/20
Coding
19/20
Instruction
19/20
Structured
14/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen/qwen3.8-27b

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View unsloth/gemma-4-26… details | View qwen/qwen3.8-27b 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