lmstudio-community/gemma-4-12b-it-qat
LM-STUDIO GGUFgemma4 · 12B · Q4_0
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
qwen3.8-27b-uncensored-hauhaucs-aggressive-mtp
LM-STUDIO GGUFqwen35 · 27B
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
75 vs 81
Hardware Fit
48 vs 64
Quality Score
86 vs 88
Hardware
lmstudio-community… qwen3.8-27b-uncens…
MachineDocker ContainerSystem manufacturer
CPUIntel Gen Intel® Core™ i9-11900HAMD Ryzen 7 5800X 8-Core Processor
Cores1616
RAM15 GB31 GB
GPUTigerLake-H GT1 [UHD Graphics]Navi 44 [Radeon RX 9060 XT]
OSUbuntu 26.04 LTSUbuntu 26.04.1 LTS
Archx64x64
Power Modeperformanceperformance
Performance
lmstudio-community… qwen3.8-27b-uncens…
Tokens/sec5.811.7
First chunk101 ms50 ms
TTFT5.3 s1.1 s
Load time11.0 sN/A
Memory usage0.6 GB15.8 GB
Memory %4%51%
HW Fit Score Breakdown
lmstudio-community/gemm…
Speed
10/50
TTFT
8/20
Memory
30/30
qwen3.8-27b-uncensored-…
Speed
19/50
TTFT
20/20
Memory
25/30
Quality
lmstudio-community/gemm…
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3.8-27b-uncensored-…
Reasoning
17/20
Coding
19/20
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
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest