Gemma 4 E4B quants compared
23 GGUF builds by real file size, probed from bartowski/google_gemma-4-e4b-it-GGUF on Hugging Face (2026-09-02). 4.5B params.
Download Gemma 4 E4B Q4_K_M (5.03 GB) — it fits 8 GB of memory with 16k context. With Ollama: ollama run gemma4:e4b
Every Gemma 4 E4B quant by real file size
| Quant | Weights | + KV (16k) | Total | Fits comfortably in | Quality |
|---|---|---|---|---|---|
| BF16 | 14.02 GB | 2.0 GB | 16.0 GB | 24 GB | Full precision (lossless) |
| Q8_0 | 7.48 GB | 2.0 GB | 9.5 GB | 12 GB | Near-lossless |
| Q6_K_L | 6.68 GB | 2.0 GB | 8.7 GB | 12 GB | Excellent |
| Q6_K | 5.9 GB | 2.0 GB | 7.9 GB | 12 GB | Excellent |
| Q5_K_L | 6.21 GB | 2.0 GB | 8.2 GB | 12 GB | Very high |
| Q5_K_M | 5.42 GB | 2.0 GB | 7.4 GB | 12 GB | Very high |
| Q5_K_S | 5.31 GB | 2.0 GB | 7.3 GB | 12 GB | Very high |
| Q4_K_M * | 5.03 GB | 2.0 GB | 7.0 GB | 8 GB | High — the default pick |
| Q4_K_L | 5.82 GB | 2.0 GB | 7.8 GB | 12 GB | High |
| Q4_1 | 5.08 GB | 2.0 GB | 7.1 GB | 8 GB | High |
| Q4_K_S | 4.88 GB | 2.0 GB | 6.9 GB | 8 GB | High |
| IQ4_NL | 4.87 GB | 2.0 GB | 6.9 GB | 8 GB | High |
| Q4_0 | 4.87 GB | 2.0 GB | 6.9 GB | 8 GB | High |
| IQ4_XS | 4.76 GB | 2.0 GB | 6.8 GB | 8 GB | High |
| Q3_K_XL | 5.48 GB | 2.0 GB | 7.5 GB | 12 GB | Acceptable — visible loss |
| Q3_K_L | 4.69 GB | 2.0 GB | 6.7 GB | 8 GB | Acceptable — visible loss |
| Q3_K_M | 4.56 GB | 2.0 GB | 6.6 GB | 8 GB | Acceptable — visible loss |
| IQ3_M | 4.44 GB | 2.0 GB | 6.4 GB | 8 GB | Acceptable — visible loss |
| Q3_K_S | 4.38 GB | 2.0 GB | 6.4 GB | 8 GB | Acceptable — visible loss |
| IQ3_XS | 4.31 GB | 2.0 GB | 6.3 GB | 8 GB | Acceptable — visible loss |
| Q2_K_L | 4.94 GB | 2.0 GB | 6.9 GB | 8 GB | Experimental — not ranked — never recommended |
| Q2_K | 4.15 GB | 2.0 GB | 6.2 GB | 8 GB | Experimental — not ranked — never recommended |
| IQ2_M | 3.69 GB | 2.0 GB | 5.7 GB | 8 GB | Experimental — not ranked — never recommended |
* default pick. Weights = real GGUF file sizes from bartowski/google_gemma-4-e4b-it-GGUF (probed 2026-09-02). KV = fp16 estimate; a q8_0 cache roughly halves it. "Comfortable" = weights + KV within 90% of memory.
Best Gemma 4 E4B quant by memory
| Memory | Recommended quant | Total (16k ctx) |
|---|---|---|
| 8 GB | Q4_K_M | 7.0 GB |
| 12 GB | Q8_0 | 9.5 GB |
| 24 GB | BF16 | 16.0 GB |
Why we don't rank Gemma 4 E4B's 2-bit quants
Quants at 2 bits per weight or below (Q2_K, IQ2, IQ1, TQ1) cut file size by roughly half versus Q4, but the quality collapse is steep and non-linear: perplexity spikes, instruction-following degrades, and hallucinations rise. A model that answers faster but wrong is not a smaller model — it is a worse one. ModelFit lists these builds for completeness but never ranks or recommends them.
Frequently asked questions
What is the best quantization of Gemma 4 E4B?
Q4_K_M is the default pick: 5.03 GB of weights, high — the default pick quality, fitting comfortably in 8 GB of memory (weights + 16k context KV-cache). Go Q6_K or Q8_0 if you have headroom.
How much memory does Gemma 4 E4B need?
At Q4_K_M, Gemma 4 E4B needs 5.03 GB for the weights plus ~2.0 GB of KV-cache at 16k context — about 7.0 GB total, so a 8 GB card or Mac (90% usable budget) runs it comfortably.
Should I use a Q2_K or IQ2 quant of Gemma 4 E4B?
No. Gemma 4 E4B at 2 bits per weight is a visibly worse model — quality collapse at that bitrate is steep, not gradual. If only a 2-bit build fits your memory, run a smaller model at Q4_K_M instead. ModelFit lists these builds but never recommends them.
Cite this page
ModelFit: Gemma 4 E4B quantization comparison (real GGUF file sizes). https://modelfit.io/quant-compare/gemma4-e4b/ (data probed 2026-09-02, CC BY 4.0).