WizardLM 2 8x22B — Hardware Requirements & GPU Compatibility
Chat
WizardLM-2 8x22B is a 140.6-billion-parameter mixture-of-experts chat model built by Microsoft's WizardLM team on top of Mixtral-8x22B-v0.1, tuned for complex chat, multilingual conversation, reasoning, and agent tasks. Microsoft briefly published it in April 2024 alongside smaller 70B and 7B siblings, then withdrew the official release within hours after disclosing that a required toxicity test had not been completed; this repository is a community mirror uploaded from the brief public window before the takedown. As an 8x22B mixture-of-experts model, it needs a multi-GPU workstation to run even quantized. Context length is 65,536 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, though as an unofficial mirror of a withdrawn release its provenance is less certain than an official checkpoint. It was published in April 2024.
10.5K downloads
416 likesSpecifications
- Publisher
- alpindale
- Parameters
- 140.6B
- Architecture
- MixtralForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2024-04-16
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does WizardLM 2 8x22B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 60.5 GB | 75.1 GB | 59.76 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 69.3 GB | 83.9 GB | 68.55 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 85.1 GB | 99.7 GB | 84.37 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 101.0 GB | 115.5 GB | 100.19 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 116.8 GB | 131.3 GB | 116.01 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 141.4 GB | 155.9 GB | 140.62 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 282.0 GB | 296.6 GB | 281.24 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 WizardLM 2 8x22B?
Q4_K_M · 85.1 GBWizardLM 2 8x22B (Q4_K_M) requires 85.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 111+ GB is recommended. Using the full 66K context window can add up to 14.6 GB, bringing total usage to 99.7 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run WizardLM 2 8x22B?
Q4_K_M · 85.1 GB18 devices with unified memory can run WizardLM 2 8x22B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Pro 16" M5 Max (128 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightWhere to Download WizardLM 2 8x22B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does WizardLM 2 8x22B need?
WizardLM 2 8x22B requires 85.1 GB of VRAM at Q4_K_M, or 282.0 GB at BF16. Full 66K context adds up to 14.6 GB (99.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 140.6B × 4.8 bits ÷ 8 = 84.4 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 15.3 GB (at full 66K context)
VRAM usage by quantization
Q4_K_M85.1 GBQ4_K_M + full context99.7 GB- Can NVIDIA GeForce RTX 5090 run WizardLM 2 8x22B?
No — WizardLM 2 8x22B requires at least 60.5 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for WizardLM 2 8x22B?
For WizardLM 2 8x22B, Q4_K_M (85.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (101.0 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 60.5 GB.
VRAM requirement by quantization
Q2_K60.5 GBQ4_K_M ★85.1 GBQ5_K_M101.0 GBQ6_K116.8 GBQ8_0141.4 GBBF16282.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run WizardLM 2 8x22B on a Mac?
WizardLM 2 8x22B requires at least 60.5 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 WizardLM 2 8x22B locally?
Yes — WizardLM 2 8x22B can run locally on consumer hardware. At Q4_K_M quantization it needs 85.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is WizardLM 2 8x22B?
At Q4_K_M, WizardLM 2 8x22B can reach ~62 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 ÷ 85.1 × 0.65 = ~131 tok/s
Estimated speed at Q4_K_M (85.1 GB)
~131 tok/s~131 tok/s~95 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of WizardLM 2 8x22B?
At Q4_K_M, the download is about 84.37 GB. The full-precision BF16 version is 281.24 GB. The smallest option (Q2_K) is 59.76 GB.
- Which GPUs can run WizardLM 2 8x22B?
No single consumer GPU has enough VRAM to run WizardLM 2 8x22B at Q4_K_M (85.1 GB). Multi-GPU or professional hardware is required.
- Which devices can run WizardLM 2 8x22B?
19 devices with unified memory can run WizardLM 2 8x22B at Q4_K_M (85.1 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.