How to Deploy Qwen3.8 2.4T A95B Locally
Qwen3.8 2.4T A95B is a MoE model with 2,446B total parameters and 95B active per token. At Q4 it needs 1,366GB of VRAM to sit entirely on the GPU; with experts offloaded to system RAM it needs only 30GB of VRAM plus 1,337GB of RAM. No single card in the database fits it; it needs multiple GPUs or the unified memory of a Mac Studio. In offload mode the cheapest card that runs it is the Instinct MI50 32GB, at roughly 2 tokens/s.
Qwen3.8 2.4T A95B details
How much VRAM does Qwen3.8 2.4T A95B need for local deployment?
MoE: all 2,446B parameters must stay resident in memory, while speed is set by the 95B active per token.
| Quantization | WeightsGB | Total at 8KGB | Total at 32KGB | Total at 128KGB |
|---|---|---|---|---|
| 1-bit | 564GGUF | 575.8 | 577.9 | 586.6 |
| 2-bit | 730.7GGUF | 910.6 | 912.8 | 921.4 |
| 3-bit | 955.5GGUF | 1,173.8 | 1,175.9 | 1,184.5 |
| 4-bit | 1,310.9GGUF | 1,365.1 | 1,367.3 | 1,375.9 |
| 5-bit | 1,650.4est. | 1,652.1 | 1,654.3 | 1,662.9 |
| 8-bit | 2,600.2GGUF | 2,537.1 | 2,539.3 | 2,547.9 |
| FP16 | 4,893.2GGUF | 4,785.6 | 4,787.7 | 4,796.3 |
Total = weights + KV cache (FP16) + 1GB runtime overhead. Weights marked GGUF are measured file sizes from the repository; the rest are estimated from bytes per parameter. Contexts beyond this model's 256K limit show a dash. Each tier takes whichever file of that bit width the repository has, preferring unsloth dynamic quants, so the exact file name varies by model.
Which GPUs can run Qwen3.8 2.4T A95B?
Xianyu
No single card in the database fits Qwen3.8 2.4T A95B: it needs at least 1,366GB of VRAM at Q4_K_M with an 8K context.
A multi-GPU build needs at least 1,366GB of VRAM in total.
None of the unified-memory machines in the database fit it either.
Recommended GPUs for Qwen3.8 2.4T A95B with CPU/GPU offloading
Xianyu
Expert weights live in system RAM (needs at least 1,337 GB); VRAM holds only attention layers, shared experts and the KV cache, at least 30 GB at Q4. Speed is bound by RAM bandwidth (estimated at 70 GB/s) and is far slower than a full-VRAM setup.
| Device | VRAMGB | Price | RAM neededGB | Est. t/s |
|---|---|---|---|---|
 Instinct MI50 32GB | 32 | $405 | 1,337 | 1.7 |
 Tesla V100 32GB | 32 | $476 | 1,337 | 1.7 |
 Arc Pro B70 | 32 | $1,465 | 1,337 | 1.5 |
| Radeon AI PRO R9700 | 32 | $1,643 | 1,337 | 1.6 |
| CMP 170HX 40GB | 40 | $1,680 | 1,337 | 1.7 |
| Radeon PRO W7800 | 32 | $1,844 | 1,337 | 1.5 |
| CMP 170HX 64GB | 64 | $2,089 | 1,337 | 1.7 |
| Instinct MI210 | 64 | $2,751 | 1,337 | 1.7 |
| Radeon PRO W7900 | 48 | $3,271 | 1,337 | 1.6 |
| RTX PRO 4500 Blackwell | 32 | $3,844 | 1,337 | 1.7 |
| GeForce RTX 4090 48GB | 48 | $3,955 | 1,337 | 1.7 |
| A100 40GB PCIe | 40 | $4,602 | 1,337 | 1.7 |
| Mac Studio M4 Max 128GB | 128 | $4,788 | 1,337 | 1.6 |
| DGX Spark 128GB | 128 | $4,832 | 1,337 | 1.4 |
| GeForce RTX 5090 D | 32 | $4,892 | 1,337 | 1.8 |
| MacBook Pro M4 Max 128GB | 128 | $5,264 | 1,337 | 1.6 |
| Mac Studio M5 Max 128GB | 128 | $5,881 | 1,337 | 1.6 |
| GeForce RTX 5090 | 32 | $6,513 | 1,337 | 1.8 |
| RTX PRO 5000 Blackwell 48GB | 48 | $6,959 | 1,337 | 1.7 |
| MacBook Pro M5 Max 128GB | 128 | $8,148 | 1,337 | 1.6 |
| RTX PRO 5000 Blackwell 72GB | 72 | $9,665 | 1,337 | 1.7 |
| RTX PRO 6000D | 84 | $10,111 | 1,337 | 1.7 |
| RTX PRO 6000 Blackwell | 96 | $18,422 | 1,337 | 1.8 |
| Mac Studio M3 Ultra 512GB | 512 | $19,315 | 1,337 | 1.6 |
| Arc Pro B65 | 32 | — | 1,337 | 1.5 |
| GeForce RTX 4080 SUPER 32GB | 32 | — | 1,337 | 1.7 |
| Instinct MI100 | 32 | — | 1,337 | 1.7 |
| Ryzen AI Max+ 395 128GB | 128 | — | 1,337 | 1.3 |
Deploy Qwen3.8 2.4T A95B locally with Ollama, llama.cpp or vLLM
The Ollama library has no official tag for it yet.
llama.cpp pulls the GGUF straight from Hugging Face; -c sets the context length.
llama-server -hf unsloth/Qwen3.8-2.4T-A95B-GGUF:Q4_K_M -c 8192
vLLM serves the original-precision weights, which needs far more memory than GGUF and usually more than one GPU.
vllm serve Qwen/Qwen3.8-2.4T-A95B
File names follow that week's model-library snapshot; the definitions are in the methodology. Methodology
FAQ
How much VRAM does Qwen3.8 2.4T A95B need?
At Q4_K_M with an 8K context Qwen3.8 2.4T A95B needs about 1,366GB of VRAM; 1,640GB leaves comfortable headroom.
What is the cheapest GPU that runs Qwen3.8 2.4T A95B?
No single card in the database fits Qwen3.8 2.4T A95B; it needs multiple GPUs or a Mac Studio's unified memory.
Can you run Qwen3.8 2.4T A95B with Ollama?
Not yet: the Ollama library has no official tag for it. You can load the GGUF with llama.cpp instead.