Qwen3-Next 80B-A3B quants compared
26 GGUF builds by real file size, probed from unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF on Hugging Face (2026-09-02). 80B params, 3B active.
Download Qwen3-Next 80B-A3B Q4_K_M (45.17 GB) — it fits 64 GB of memory with 16k context. With Ollama: ollama run qwen3-next:80b
Every Qwen3-Next 80B-A3B quant by real file size
| Quant | Weights | + KV (16k) | Total | Fits comfortably in | Quality |
|---|---|---|---|---|---|
| BF16 | 148.51 GB | 0.4 GB | 148.9 GB | >128 GB | Full precision (lossless) |
| Q8_K_XL | 86.68 GB | 0.4 GB | 87.1 GB | 128 GB | Near-lossless |
| Q8_0 | 78.99 GB | 0.4 GB | 79.4 GB | 96 GB | Near-lossless |
| Q6_K_XL | 63.81 GB | 0.4 GB | 64.2 GB | 96 GB | Excellent |
| Q6_K | 61.04 GB | 0.4 GB | 61.4 GB | 96 GB | Excellent |
| Q5_K_M | 52.91 GB | 0.4 GB | 53.3 GB | 64 GB | Very high |
| Q5_K_XL | 52.77 GB | 0.4 GB | 53.1 GB | 64 GB | Very high |
| Q5_K_S | 51.24 GB | 0.4 GB | 51.6 GB | 64 GB | Very high |
| Q4_K_M * | 45.17 GB | 0.4 GB | 45.5 GB | 64 GB | High — the default pick |
| Q4_1 | 46.62 GB | 0.4 GB | 47.0 GB | 64 GB | High |
| Q4_K_XL | 42.9 GB | 0.4 GB | 43.3 GB | 64 GB | High |
| Q4_K_S | 42.38 GB | 0.4 GB | 42.8 GB | 48 GB | High |
| Q4_0 | 42.2 GB | 0.4 GB | 42.6 GB | 48 GB | High |
| IQ4_NL | 42.01 GB | 0.4 GB | 42.4 GB | 48 GB | High |
| IQ4_XS | 39.72 GB | 0.4 GB | 40.1 GB | 48 GB | High |
| Q3_K_M | 35.67 GB | 0.4 GB | 36.0 GB | 48 GB | Acceptable — visible loss |
| Q3_K_XL | 33.19 GB | 0.4 GB | 33.6 GB | 48 GB | Acceptable — visible loss |
| Q3_K_S | 32.21 GB | 0.4 GB | 32.6 GB | 48 GB | Acceptable — visible loss |
| IQ3_XXS | 30.82 GB | 0.4 GB | 31.2 GB | 48 GB | Acceptable — visible loss |
| Q2_K_XL | 28.06 GB | 0.4 GB | 28.4 GB | 32 GB | Experimental — not ranked — never recommended |
| Q2_K_L | 27.24 GB | 0.4 GB | 27.6 GB | 32 GB | Experimental — not ranked — never recommended |
| Q2_K | 27.17 GB | 0.4 GB | 27.5 GB | 32 GB | Experimental — not ranked — never recommended |
| IQ2_XXS | 24.41 GB | 0.4 GB | 24.8 GB | 32 GB | Experimental — not ranked — never recommended |
| IQ1_M | 22.73 GB | 0.4 GB | 23.1 GB | 32 GB | Experimental — not ranked — never recommended |
| IQ1_S | 21.33 GB | 0.4 GB | 21.7 GB | 32 GB | Experimental — not ranked — never recommended |
| TQ1_0 | 19.06 GB | 0.4 GB | 19.4 GB | 24 GB | Experimental — not ranked — never recommended |
* default pick. Weights = real GGUF file sizes from unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF (probed 2026-09-02). KV = fp16 estimate; a q8_0 cache roughly halves it. "Comfortable" = weights + KV within 90% of memory.
Best Qwen3-Next 80B-A3B quant by memory
| Memory | Recommended quant | Total (16k ctx) |
|---|---|---|
| 48 GB | Q4_0 | 42.6 GB |
| 64 GB | Q5_K_M | 53.3 GB |
| 96 GB | Q8_0 | 79.4 GB |
Why we don't rank Qwen3-Next 80B-A3B'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 Qwen3-Next 80B-A3B?
Q4_K_M is the default pick: 45.17 GB of weights, high — the default pick quality, fitting comfortably in 64 GB of memory (weights + 16k context KV-cache). Go Q6_K or Q8_0 if you have headroom.
How much memory does Qwen3-Next 80B-A3B need?
At Q4_K_M, Qwen3-Next 80B-A3B needs 45.17 GB for the weights plus ~0.4 GB of KV-cache at 16k context — about 45.5 GB total, so a 64 GB card or Mac (90% usable budget) runs it comfortably.
Should I use a Q2_K or IQ2 quant of Qwen3-Next 80B-A3B?
No. Qwen3-Next 80B-A3B 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: Qwen3-Next 80B-A3B quantization comparison (real GGUF file sizes). https://modelfit.io/quant-compare/qwen3-next-80b-a3b/ (data probed 2026-09-02, CC BY 4.0).