Comfy-Org · video
Wan_2.2_ComfyUI_Repackaged
Comfy-Org/Wan_2.2_ComfyUI_RepackagedWan_2.2_ComfyUI_Repackaged at Q4_K_M is exactly 73,954,290,816 bytes (68.88 GiB / 73.95 GB)
From the file· summed from 7 file(s)
Parameters
—
Architecture
pig
Context
—
native (config.json)
License
apache-2.0
Shipped quantizations
● exact bytes, summed from published files
| Quant | Size● | Exact bytes● | Effective bpw● | Tensors● | Publisher |
|---|---|---|---|---|---|
| TQ1_0 | 1.31 GiB | 1,405,000,416 | — | — | calcuis |
| TQ2_0 | 1.52 GiB | 1,635,031,776 | — | — | calcuis |
| F162 shards | 1.55 GiB | 1,663,436,960 | — | — | calcuis |
| IQ3_XXS | 2.09 GiB | 2,248,448,736 | — | — | calcuis |
| IQ3_S | 2.31 GiB | 2,478,480,096 | — | — | calcuis |
| Q2_K_S | 8.86 GiB | 9,510,895,200 | — | — | calcuis |
| Q2_K7 shards | 42.63 GiB | 45,778,889,856 | — | — | calcuis |
| Q3_K_S7 shards | 50.03 GiB | 53,717,101,696 | — | — | calcuis |
| Q3_K_M7 shards | 53.96 GiB | 57,936,702,592 | — | — | calcuis |
| Q3_K_L7 shards | 57.58 GiB | 61,827,181,696 | — | — | calcuis |
| IQ4_XS7 shards | 58.65 GiB | 62,976,048,000 | — | — | calcuis |
| IQ4_NL7 shards | 61.31 GiB | 65,829,485,440 | — | — | calcuis |
| Q4_K_S7 shards | 63.53 GiB | 68,216,089,728 | — | — | calcuis |
| Q4_09 shards | 68.43 GiB | 73,476,309,504 | — | — | calcuis |
| Q4_K_M7 shards | 68.88 GiB | 73,954,290,816 | — | — | calcuis |
| Q4_18 shards | 69.67 GiB | 74,804,305,376 | — | — | calcuis |
| Q5_K_S7 shards | 71.95 GiB | 77,257,960,576 | — | — | calcuis |
| Q5_K_M7 shards | 75.84 GiB | 81,435,880,576 | — | — | calcuis |
| Q5_08 shards | 76.40 GiB | 82,029,997,280 | — | — | calcuis |
| Q5_18 shards | 80.87 GiB | 86,831,472,096 | — | — | calcuis |
| Q6_K7 shards | 83.25 GiB | 89,385,069,696 | — | — | calcuis |
| Q8_08 shards | 108.86 GiB | 116,884,663,520 | — | — | calcuis |
Compare with
same modality, comparable size
Will it run on your card?
full quant x context sweep
Radeon RX 6500 XT 4GBGeForce RTX 3050 6GBGeForce RTX 5050 8GBGeForce RTX 3080 10GBGeForce RTX 2080 Ti 11GBGeForce RTX 5070 12GBGeForce RTX 5060 Ti 16GBApple M3 Pro 18GBGeForce RTX 3080 Ti 20GBGeForce RTX 5090 D V2 24GBGeForce RTX 5090 D 32GBApple M5 Max 36GBApple M5 Pro 48GBApple M5 Max 64GBApple M3 Ultra 96GBApple M5 Max 128GBApple M2 Ultra 192GBApple M3 Ultra 256GBApple M3 Ultra 512GB
Why other calculators give a different number
A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 0.00 GiB. The real file is 68.88 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.
Architecture
Architecture unavailable — this repository is gated and no ungated mirror was found. Exact file sizes above are still authoritative; only the KV math needs the config.
Questions people ask
- How much VRAM does Wan_2.2_ComfyUI_Repackaged need?
- Q4_K_M is exactly 73,954,290,816 bytes (68.88 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
- Which quantization of Wan_2.2_ComfyUI_Repackaged 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.