codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
unsloth/gemma-4-e4b-it-qat
LM-STUDIO GGUFgemma4 · Q4_K_XL
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
67 vs 79
Hardware Fit
67 vs 69
Quality Score
67 vs 83
Hardware
codestral:22b unsloth/gemma-4-e4…
MachineNVIDIA NVIDIA_DGX_SparkDocker Container
CPUCortex-X925Intel Gen Intel® Core™ i9-11900H
Cores2016
RAM122 GB15 GB
GPUDevice 2e12TigerLake-H GT1 [UHD Graphics]
OSUbuntu 24.04.4 LTSUbuntu 26.04 LTS
Archarm64x64
Power Modeperformanceperformance
Performance
codestral:22b unsloth/gemma-4-e4…
Tokens/sec17.212.1
First chunk129 ms40 ms
TTFT129 ms2.1 s
Load time11.6 s7.2 s
Memory usage18.9 GB0.8 GB
Memory %16%6%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
unsloth/gemma-4-e4b-it-…
Speed
22/50
TTFT
17/20
Memory
30/30
Quality
codestral:22b
Reasoning
11/20
Coding
17/20
Instruction
9/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
unsloth/gemma-4-e4b-it-…
Reasoning
15/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate 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