Qwen3.8 Distill 35B A3B Coder Abliterated — Hardware Requirements & GPU Compatibility
ChatCode
Qwen3.8 Distill 35B A3B Coder Abliterated is a 35B-parameter open language model from Lord-H4D3ZS in the Qwen 3.8 family. It supports a context window of up to 262,144 tokens. At BF16 it needs about 70.38 GB of VRAM — see which GPUs and Macs can run it below.
38.0K downloads
9 likesSpecifications
- Publisher
- Lord-H4D3ZS
- Family
- Qwen 3.8
- Parameters
- 35B
- Architecture
- Qwen3_5MoeForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-08-15
- License
- Apache 2.0
Get Started
How Much VRAM Does Qwen3.8 Distill 35B A3B Coder Abliterated Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 70.4 GB | 81.0 GB | 70.00 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Qwen3.8 Distill 35B A3B Coder Abliterated?
BF16 · 70.4 GBQwen3.8 Distill 35B A3B Coder Abliterated (BF16) requires 70.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 92+ GB is recommended. Using the full 262K context window can add up to 10.7 GB, bringing total usage to 81.0 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Qwen3.8 Distill 35B A3B Coder Abliterated?
BF16 · 70.4 GB19 devices with unified memory can run Qwen3.8 Distill 35B A3B Coder Abliterated, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 96GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Qwen3.8 Distill 35B A3B Coder Abliterated need?
Qwen3.8 Distill 35B A3B Coder Abliterated requires 70.4 GB of VRAM at BF16. Full 262K context adds up to 10.7 GB (81.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 35B × 16 bits ÷ 8 = 70 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 11 GB (at full 262K context)
VRAM usage by quantization
BF1670.4 GBBF16 + full context81.0 GB- Can NVIDIA GeForce RTX 5090 run Qwen3.8 Distill 35B A3B Coder Abliterated?
No — Qwen3.8 Distill 35B A3B Coder Abliterated requires at least 70.4 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Qwen3.8 Distill 35B A3B Coder Abliterated on a Mac?
Qwen3.8 Distill 35B A3B Coder Abliterated requires at least 70.4 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Qwen3.8 Distill 35B A3B Coder Abliterated locally?
Yes — Qwen3.8 Distill 35B A3B Coder Abliterated can run locally on consumer hardware. At BF16 quantization it needs 70.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwen3.8 Distill 35B A3B Coder Abliterated?
At BF16, Qwen3.8 Distill 35B A3B Coder Abliterated can reach ~68 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 70.4 × 0.65 = ~74 tok/s
Estimated speed at BF16 (70.4 GB)
~74 tok/s~74 tok/s~68 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Qwen3.8 Distill 35B A3B Coder Abliterated?
At BF16, the download is about 70.00 GB.
- Which GPUs can run Qwen3.8 Distill 35B A3B Coder Abliterated?
No single consumer GPU has enough VRAM to run Qwen3.8 Distill 35B A3B Coder Abliterated at BF16 (70.4 GB). Multi-GPU or professional hardware is required.
- Which devices can run Qwen3.8 Distill 35B A3B Coder Abliterated?
19 devices with unified memory can run Qwen3.8 Distill 35B A3B Coder Abliterated at BF16 (70.4 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.