Gemma 4 E2B
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M unsloth/gemma-4-E2B-it-GGUF | 2.89 GiB | 1 | unknown | 8 GB GPU (cache unknown) | HF files |
| Q5_K_M unsloth/gemma-4-E2B-it-GGUF | 3.13 GiB | 1 | unknown | 8 GB GPU (cache unknown) | HF files |
| Q8_0 unsloth/gemma-4-E2B-it-GGUF | 4.70 GiB | 1 | unknown | 8 GB GPU (cache unknown) | HF files |
| MLX 4-bit mlx-community/gemma-4-E2B-it-4bit | 3.31 GiB | 1 | unknown | 8 GB Mac (cache unknown) | HF files |
| MLX 8-bit mlx-community/gemma-4-E2B-it-8bit | 5.46 GiB | 2 | unknown | 16 GB Mac (cache unknown) | HF files |
No verified file: FP16. Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory.
Quality
Artificial Analysis Intelligence Index
7.8 AA estimate
Variant: Gemma 4 E2B (Reasoning) · observed 2026-10-17 · source
Rank #72 of 75 researched 2026 models.
Arena text rating
Unknown
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 0
No reported measurement yet. Submit one.
Community threads
- [Exploration] Applying Native Dual-Regime & KV-Cache Handoff to this model variant? Hugging Face · 2026-09-21
- Chat template may re-inject prior-turn reasoning during multi-turn tool use → repetition loops Hugging Face · 2026-06-10
Qualitative signals only; titles are not verified claims.