gemma-4-E4B-it
unsloth/gemma-4-E4B-itgemma-4-E4B-it at Q4_K_M is exactly 4,977,164,544 bytes (4.64 GiB / 4.98 GB) — an effective 4.980 bits per weight, not the nominal 4. Its KV cache at 32K is 0.51 GiB, not the 2.63 GiB a flat formula predicts.
Shipped quantizations
| Quant | Size● | Exact bytes● | Effective bpw● | Tensors● | Publisher |
|---|---|---|---|---|---|
| UD-IQ2_M | 3.29 GiB | 3,530,227,968 | 3.532 | — | dahara1 |
| UD-IQ3_XXS | 3.45 GiB | 3,702,259,968 | 3.704 | — | dahara1 |
| Q3_K_S | 3.60 GiB | 3,862,372,608 | 3.864 | — | dahara1 |
| Q3_K_M | 3.78 GiB | 4,058,130,688 | 4.060 | — | dahara1 |
| IQ4_XS | 4.39 GiB | 4,715,409,664 | 4.718 | — | dahara1 |
| IQ4_NL | 4.50 GiB | 4,835,832,064 | 4.838 | — | dahara1 |
| Q4_0 | 4.50 GiB | 4,835,995,904 | 4.838 | — | dahara1 |
| Q4_K_S | 4.51 GiB | 4,844,843,264 | 4.847 | — | dahara1 |
| Q4_K_M | 4.64 GiB | 4,977,164,544 | 4.980 | — | dahara1 |
| Q4_1 | 4.73 GiB | 5,074,383,104 | 5.077 | — | dahara1 |
| Q4_K_M | 4.97 GiB | 5,335,275,936 | 5.338 | — | pankajpandey-dev |
| Q4_K_M | 4.97 GiB | 5,335,290,240 | 5.338 | — | trjxter |
| Q5_K_S | 5.03 GiB | 5,404,848,384 | 5.407 | — | dahara1 |
| Q5_K_M | 5.11 GiB | 5,481,791,744 | 5.484 | — | dahara1 |
| Q5_K_M | 5.37 GiB | 5,762,898,336 | 5.766 | — | pankajpandey-dev |
| Q5_K_M | 5.37 GiB | 5,762,912,640 | 5.766 | — | trjxter |
| Q6_K | 5.79 GiB | 6,217,261,440 | 6.220 | — | trjxter |
| Q6_K | 5.95 GiB | 6,392,299,776 | 6.395 | — | dahara1 |
| Q8_0 | 7.48 GiB | 8,031,226,272 | 8.035 | — | pankajpandey-dev |
| Q8_0 | 7.48 GiB | 8,031,240,576 | 8.035 | — | trjxter |
| Q8_0 | 7.63 GiB | 8,192,946,432 | 8.197 | — | dahara1 |
KV cache by context
| Context | KV cache (f16)● | Flat formula | Overstated by | Full / windowed / recurrent |
|---|---|---|---|---|
| 4,096 | 0.12 GiB | 0.33 GiB | 2.67× | 7 / 35 / 0 |
| 8,192 | 0.18 GiB | 0.66 GiB | 3.69× | 7 / 35 / 0 |
| 16,384 | 0.29 GiB | 1.31 GiB | 4.57× | 7 / 35 / 0 |
| 32,768 | 0.51 GiB | 2.63 GiB | 5.19× | 7 / 35 / 0 |
| 65,536 | 0.94 GiB | 5.25 GiB | 5.57× | 7 / 35 / 0 |
| 131,072 | 1.82 GiB | 10.50 GiB | 5.77× | 7 / 35 / 0 |
35 of 42 layers cache only a 512-token window rather than the full context, on a period of . Figures assume the default configuration; --swa-full disables the saving entirely.
Compare with
Will it run on your card?
Why other calculators give a different number
A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 4.19 GiB. The real file is 4.64 GiB, because a quantization is a mixture and some tensors are always kept at higher precision. The larger discrepancy is the cache: a flat formula gives 2.63 GiB at 32K context where the real figure is 0.51 GiB, because most of this model's layers cache a fixed window rather than the whole context.
Architecture
Questions people ask
- How much VRAM does gemma-4-E4B-it need?
- Q4_K_M is exactly 4,977,164,544 bytes (4.64 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
- How large is gemma-4-E4B-it's KV cache?
- 0.51 GiB at 32K context with an f16 cache, computed per layer. Quantizing the cache to q8_0 roughly halves it, which is often the difference between a context length fitting and not.
- Which quantization of gemma-4-E4B-it should I use?
- Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.