Can you run AliceAI Foundation 80B A3B Base locally?
AliceAI family · 2026 · 81.3B parameters (3B activated per token) · Hugging Face model card
AliceAI Foundation 80B A3B Base is a mixture-of-experts model with 3B activated parameters per token and 80B-class total open weights (official card: 80B total / 3B active; HF safetensors.total=81,286,433,408). Native context is 262,144 tokens, apache-2.0. Local VRAM fit uses the 3B active count, not the 80B dense-equivalent: roughly 8 GB at Q4-class (calculated). Weights still occupy ~80B-class disk. Measured speeds: not yet published here.
Minimum: 8 GB+ memory (Q4-class on 3B active, calculated) · Recommended: 8 GB+ for comfortable context headroom (Q4-class on 3B active, calculated)
How much VRAM does AliceAI Foundation 80B A3B Base need at each quantization?
AliceAI Foundation 80B A3B Base needs 54.1 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level with 4k and 32k token contexts.
| Quantization | Bits / weight | Weights only | Total + KV @4k ctx | Total + KV @32k ctx |
|---|---|---|---|---|
| Q4_K_M | 4.8 | 48.8 GB | 54.1 GB | 56.9 GB |
| Q5_K_M | 5.7 | 57.9 GB | 64.1 GB | 66.9 GB |
| Q6_K | 6.6 | 67.1 GB | 74.2 GB | 77.0 GB |
| Q8_0 | 8.5 | 86.4 GB | 95.4 GB | 98.2 GB |
| FP16 | 16 | 162.6 GB | 179.2 GB | 182.1 GB |
hybrid KDA + gated attention; MoE 10/512 + 1 shared
Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (48 layers, 2 KV heads, 256 head dim). Source: HF-verified 2026-09-21 via api (gated=false params=81.29B safetensors.total=81286433408 ctx=262144 license=apache-2.0 repo=yandex/AliceAI-Foundation-80B-A3B-Base@641d8820dd13db8201b1d88e635c5b21ee247568 layers=48 kv_heads=2). MoE: num_experts=512 num_experts_per_tok=10 active_params_b=3.0 (official README (80B total, 3B active)). VRAM figures are documented calculations, not measurements. No tok/s invented.
Which GPUs can run AliceAI Foundation 80B A3B Base locally?
At Q4_K_M with a 4k context, AliceAI Foundation 80B A3B Base needs 54.1 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.
Runs AliceAI Foundation 80B A3B Base comfortably (25%+ VRAM headroom)
| GPU | VRAM | Bandwidth | Type | |
|---|---|---|---|---|
| H100 SXM | 80 GB | 3350 GB/s | Data Center GPU | |
| NVIDIA A100 80GB SXM | 80 GB | 2039 GB/s | Data Center GPU | |
| NVIDIA H100 PCIe 80GB | 80 GB | 2039 GB/s | Data Center GPU | |
| NVIDIA RTX PRO 6000 Blackwell | 96 GB | 1792 GB/s | Pro GPU | Check price |
| H200 SXM | 141 GB | 4800 GB/s | Data Center GPU | |
| AMD Instinct MI300X | 192 GB | 5300 GB/s | Data Center GPU | |
| NVIDIA B200 | 192 GB | 8000 GB/s | Data Center GPU | |
| AMD Instinct MI325X | 256 GB | 6000 GB/s | Data Center GPU | |
| AMD Instinct MI355X | 288 GB | 8000 GB/s | Data Center GPU | |
| NVIDIA B300 (Blackwell Ultra) | 288 GB | 8000 GB/s | Data Center GPU |
Needs 2+ GPUs to run AliceAI Foundation 80B A3B Base
One of these cards is too small on its own, but a pair (tensor or pipeline parallel, ~90% efficiency) covers the 54.1 GB requirement. See our multi-GPU guide for setup.
| GPU | VRAM | Bandwidth | Type | |
|---|---|---|---|---|
| AMD Radeon Pro W7800 | 32 GB ×2 | 576 GB/s | Pro GPU | Check price |
| GeForce RTX 5090 | 32 GB ×2 | 1792 GB/s | Consumer GPU | Check price |
| NVIDIA RTX 5000 Ada | 32 GB ×2 | 576 GB/s | Pro GPU | Check price |
| NVIDIA RTX PRO 4500 Blackwell | 32 GB ×2 | 896 GB/s | Pro GPU | Check price |
| NVIDIA A100 40GB SXMEOL | 40 GB ×2 | 1555 GB/s | Data Center GPU | |
| AMD Radeon Pro W7900 | 48 GB ×2 | 864 GB/s | Pro GPU | Check price |
| NVIDIA RTX PRO 5000 Blackwell | 48 GB ×2 | 1344 GB/s | Pro GPU | |
| RTX 6000 Ada | 48 GB ×2 | 960 GB/s | Pro GPU | Check price |
| RTX A6000 | 48 GB ×2 | 768 GB/s | Pro GPU | Check price |
Can a Mac run AliceAI Foundation 80B A3B Base?
Yes — these Apple Silicon machines fit AliceAI Foundation 80B A3B Base at Q4_K_M, since macOS lets the GPU use about 75% of unified memory. Generation speed is bound by memory bandwidth, so the GB/s column matters as much as capacity.
| Apple Silicon | Unified memory | Usable by GPU (~75%) | Bandwidth |
|---|---|---|---|
| M3 Ultra (Mac Studio, 96 GB) | 96 GB | 72 GB | 819 GB/s |
| Apple M3 Max | 128 GB | 96 GB | 400 GB/s |
| M4 Max (MacBook Pro) | 128 GB | 96 GB | 546 GB/s |
| M3 Ultra (Mac Studio, 256 GB) | 256 GB | 192 GB | 819 GB/s |
Can AliceAI Foundation 80B A3B Base run on mini PCs, Jetson, or NPU devices?
These edge and NPU devices from our database have enough memory for AliceAI Foundation 80B A3B Base at Q4_K_M. Their memory bandwidth is far below discrete GPUs, so expect a fraction of desktop generation speed.
| Device | Memory | Bandwidth | Type |
|---|---|---|---|
| Jetson AGX Orin 64GB | 64 GB | 204 GB/s | Edge Compute Device |
| Snapdragon X Elite (X1E-84-100) | 64 GB | 135 GB/s | NPU Chip |
| AMD Ryzen AI 9 HX 370 (Strix Point) | 96 GB | 120 GB/s | NPU Chip |
Which pre-built systems can run AliceAI Foundation 80B A3B Base?
These mini PCs and workstations from our database fit AliceAI Foundation 80B A3B Base at Q4_K_M. Usable-memory figures are conservative: Windows shares about half of system RAM with the GPU by default (Linux can expose more), macOS lets Apple Silicon GPUs use about 75% of unified memory, and Linux unified-memory systems such as GB10 expose roughly 90%. Generation speed is bound by memory bandwidth, so compare the GB/s column before buying.
| System | Type | Memory | Usable for AI | Bandwidth | GPUs |
|---|---|---|---|---|---|
| AMD Ryzen AI Halo Developer Platform (Max+ 395) | Mini PC | 128 GB | 64 GB | 256 GB/s | — |
| ArsenalPC MES2X Dual RTX 5090 AI Workstation | Workstation | 64 GB | 64 GB | — | 2 |
| GMKtec EVO-X2 (Ryzen AI Max+ 395) | Mini PC | 128 GB | 64 GB | 256 GB/s | — |
| MinisForum MS-S1 MAX (Ryzen AI Max+ 395) | Mini PC | 128 GB | 64 GB | 256 GB/s | — |
| BOXX APEXX 8R (1x RTX PRO 6000 Blackwell) | Workstation | 96 GB | 96 GB | 1792 GB/s | 1 |
| GEEKOM A9 Mega AI Workstation | Workstation | 128 GB | 96 GB | — | 1 |
| NOVATECH RTX PRO 6000 AI Workstation | Workstation | 96 GB | 96 GB | — | 1 |
| System76 Thelio Major (1x RTX PRO 6000 Blackwell) | Workstation | 96 GB | 96 GB | 1792 GB/s | 1 |
| System76 Thelio Major (2x RTX 6000 Ada) | Workstation | 96 GB | 96 GB | 960 GB/s | 2 |
| Lenovo ThinkStation PGX | Workstation | 128 GB | 115.2 GB | 273 GB/s | 1 |
| NVIDIA DGX Spark | Workstation | 128 GB | 115.2 GB | 273 GB/s | 1 |
| BIZON G3000 G2 (4x RTX 5090) | Workstation | 128 GB | 128 GB | 1792 GB/s | 4 |
| Apple Mac Studio M2 Ultra (192GB) | Workstation | 192 GB | 144 GB | 800 GB/s | 1 |
| HP Z8 Fury G5 (4x RTX 6000 Ada) | Workstation | 192 GB | 192 GB | 960 GB/s | 4 |