Gemma-4-E4B-Luchador
rpDungeon/Gemma-4-E4B-LuchadorGemma-4-E4B-Luchador at Q4_K_M is exactly 5,405,168,288 bytes (5.03 GiB / 5.41 GB) — an effective 5.408 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 |
|---|---|---|---|---|---|
| IQ2_M | 3.69 GiB | 3,959,906,976 | 3.962 | — | bartowski |
| Q2_K | 4.15 GiB | 4,458,091,168 | 4.460 | — | bartowski |
| IQ3_XS | 4.31 GiB | 4,632,038,048 | 4.634 | — | bartowski |
| Q3_K_S | 4.38 GiB | 4,699,693,728 | 4.702 | — | bartowski |
| IQ3_M | 4.44 GiB | 4,767,779,488 | 4.770 | — | bartowski |
| Q3_K_M | 4.56 GiB | 4,898,728,608 | 4.901 | — | bartowski |
| Q3_K_L | 4.69 GiB | 5,034,224,288 | 5.037 | — | bartowski |
| IQ4_XS | 4.76 GiB | 5,112,826,528 | 5.115 | — | bartowski |
| Q4_0 | 4.87 GiB | 5,223,858,848 | 5.226 | — | bartowski |
| IQ4_NL | 4.87 GiB | 5,232,224,928 | 5.235 | — | bartowski |
| Q4_K_S | 4.88 GiB | 5,235,655,328 | 5.238 | — | bartowski |
| Q2_K_L | 4.94 GiB | 5,303,243,424 | 5.306 | — | bartowski |
| Q4_K_M | 5.03 GiB | 5,405,168,288 | 5.408 | — | bartowski |
| Q4_1 | 5.08 GiB | 5,458,477,728 | 5.461 | — | bartowski |
| Q5_K_S | 5.31 GiB | 5,701,288,608 | 5.704 | — | bartowski |
| Q5_K_M | 5.42 GiB | 5,820,881,568 | 5.824 | — | bartowski |
| Q4_K_L | 5.82 GiB | 6,250,320,544 | 6.253 | — | bartowski |
| Q6_K | 5.90 GiB | 6,329,952,928 | 6.333 | — | bartowski |
| Q5_K_L | 6.21 GiB | 6,666,033,824 | 6.669 | — | bartowski |
| Q6_K_L | 6.68 GiB | 7,175,105,184 | 7.179 | — | bartowski |
| Q8_0 | 7.48 GiB | 8,031,240,864 | 8.035 | — | bartowski |
| BF16 | 14.02 GiB | 15,053,095,264 | 15.060 | — | bartowski |
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 5.03 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-Luchador need?
- Q4_K_M is exactly 5,405,168,288 bytes (5.03 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-Luchador'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-Luchador 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.