Qwen3 Coder 480B A35B Instruct Heretic — Hardware Requirements & GPU Compatibility
ChatCode
Qwen3 Coder 480B A35B Instruct Heretic is a 480.2B-parameter open language model from jarradh in the Qwen 3 family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 288.65 GB of VRAM — see which GPUs and Macs can run it below.
59 downloads
1 likesSpecifications
- Publisher
- jarradh
- Family
- Qwen 3
- Parameters
- 480.2B
- Architecture
- Qwen3MoeForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-02-04
- License
- Apache 2.0
Get Started
How Much VRAM Does Qwen3 Coder 480B A35B Instruct Heretic Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 204.6 GB | 237.7 GB | 204.07 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 234.6 GB | 267.7 GB | 234.08 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 288.6 GB | 321.7 GB | 288.09 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 342.7 GB | 375.7 GB | 342.11 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 396.7 GB | 429.7 GB | 396.13 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 480.7 GB | 513.7 GB | 480.15 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 960.9 GB | 993.9 GB | 960.31 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 Coder 480B A35B Instruct Heretic?
Q4_K_M · 288.6 GBQwen3 Coder 480B A35B Instruct Heretic (Q4_K_M) requires 288.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 376+ GB is recommended. Using the full 262K context window can add up to 33.0 GB, bringing total usage to 321.7 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Qwen3 Coder 480B A35B Instruct Heretic?
Q4_K_M · 288.6 GB3 devices with unified memory can run Qwen3 Coder 480B A35B Instruct Heretic, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 512GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightWhere to Download Qwen3 Coder 480B A35B Instruct Heretic
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Qwen3 Coder 480B A35B Instruct Heretic need?
Qwen3 Coder 480B A35B Instruct Heretic requires 288.6 GB of VRAM at Q4_K_M, or 960.9 GB at BF16. Full 262K context adds up to 33.0 GB (321.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 480.2B × 4.8 bits ÷ 8 = 288.1 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 33.6 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M288.6 GBQ4_K_M + full context321.7 GB- Can NVIDIA GeForce RTX 5090 run Qwen3 Coder 480B A35B Instruct Heretic?
No — Qwen3 Coder 480B A35B Instruct Heretic requires at least 204.6 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for Qwen3 Coder 480B A35B Instruct Heretic?
For Qwen3 Coder 480B A35B Instruct Heretic, Q4_K_M (288.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (342.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 204.6 GB.
VRAM requirement by quantization
Q2_K204.6 GBQ4_K_M ★288.6 GBQ5_K_M342.7 GBQ6_K396.7 GBQ8_0480.7 GBBF16960.9 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwen3 Coder 480B A35B Instruct Heretic on a Mac?
Qwen3 Coder 480B A35B Instruct Heretic requires at least 204.6 GB at Q2_K, 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 Coder 480B A35B Instruct Heretic locally?
Yes — Qwen3 Coder 480B A35B Instruct Heretic can run locally on consumer hardware. At Q4_K_M quantization it needs 288.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of Qwen3 Coder 480B A35B Instruct Heretic?
At Q4_K_M, the download is about 288.09 GB. The full-precision BF16 version is 960.31 GB. The smallest option (Q2_K) is 204.07 GB.
- Which GPUs can run Qwen3 Coder 480B A35B Instruct Heretic?
No single consumer GPU has enough VRAM to run Qwen3 Coder 480B A35B Instruct Heretic at Q4_K_M (288.6 GB). Multi-GPU or professional hardware is required.
- Which devices can run Qwen3 Coder 480B A35B Instruct Heretic?
3 devices with unified memory can run Qwen3 Coder 480B A35B Instruct Heretic at Q4_K_M (288.6 GB), including Mac Studio (M3 Ultra, 512GB), NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.