hf.co/unsloth/gemma-4-E2B-it-GGUF:UD-Q8_K_XL
OLLAMA GGUFgemma4 · 4.65B · unknown
Aug 23, 2026 · Apple M1 Pro
codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
84 vs 67
Hardware Fit
99 vs 67
Quality Score
77 vs 67
Hardware
hf.co/unsloth/gemm… codestral:22b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M1 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M1 ProDevice 2e12
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
hf.co/unsloth/gemm… codestral:22b
Tokens/sec48.017.2
First chunk167 ms129 ms
TTFT167 ms129 ms
Load time4.7 s11.6 s
Memory usage5.3 GB18.9 GB
Memory %33%16%
HW Fit Score Breakdown
hf.co/unsloth/gemma-4-E…
Speed
50/50
TTFT
20/20
Memory
29/30
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
Quality
hf.co/unsloth/gemma-4-E…
Reasoning
12/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
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
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