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under the Apache 2.0 license, permitting unrestricted commercial and research use, though as an unofficial mirror of a withdrawn release its provenance is less certain than an official checkpoint.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.
WizardLM 2 8x22B runs on a 96 GB+ Mac or a workstation GPU
Best local pick → Mac Studio (M3 Ultra, 96GB) · Q4_K_M · 88.4 GB · ~19 tok/s
Macs from 48 GB (IQ2_XXS · ~27 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run WizardLM 2 8x22B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/mradermacher/WizardLM-2-8x22B-i1-GGUFQ4_K_M · needs ~88.4 GB · 16K context
Download: WizardLM-2-8x22B-i1-Q4_K_M.gguf84.37 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on H200 (141 GB) (52 GB headroom) · Q4_K_M
- Generation speed
- ~94 tok/s
- generation speed
- Cost per 1M output tokens
- $10.64
- per 1M output tokens
How Much VRAM Does WizardLM 2 8x22B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 39.4 GB | 46.5 GB | 2-bit · i-quant extreme compression — Importance-weighted 2-bit, extreme compression — significant quality loss | Does not fit: needs 42.7 GB | |
| 43.0 GB | 50 GB | 2-bit · i-quant extra small — Importance-weighted 2-bit, extra small | Does not fit: needs 46.3 GB | |
| 60.5 GB | 67.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Does not fit: needs 63.8 GB | |
| 69.3 GB | 76.4 GB | 3-bit medium — 3-bit medium quantization | Does not fit: needs 72.6 GB | |
| 85.1 GB | 92.2 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Does not fit: needs 88.4 GB | |
| 101.0 GB | 108 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 104.3 GB | |
| 116.8 GB | 123.8 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 120.1 GB | |
| 141.4 GB | 148.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 144.7 GB |
Selected Q4_K_M
4-bit medium quantization88.4GBat 16K context
- Weights
- 84.4 GB
- KV cache
- 3.8 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 64.4 GB more
Or .
Which Hardware 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 consumer GPU has enough memory. 30 devices with unified memory can run WizardLM 2 8x22B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 96GB).
64–80 GB
Q4_K_M · best fit Q2_K (63.8 GB)
1 device family
Orin~8Simulate output on NVIDIA Jetson AGX Orin 64GB96 GB
fits · 7.6 GB free · up to 32K ctx
2 Mac classes
M3 Ultra*96 GB~19Simulate output on Mac Studio (M3 Ultra, 96GB)M3 Max*96 GB~8Simulate output on MacBook Pro 14" M3 Max (96 GB)
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is WizardLM 2 8x22B?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
Here are all 3 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- GPQA Diamond
Epoch AI · Apr 2024Independent
Independent43.4%
#69/100 open
- MMLU-Pro
TIGER-LabIndependent
Independent39.2%
#103/146 open
- MATH Level 5
Epoch AI · Apr 2024Independent
Independent25.7%
#25/39 open
Similar models
1| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Mixtral 8x22B Instruct v0.1Mistral AI | 72.2 | 88.4 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- alpindale
- Parameters
- 140.6B
- Active parameters
- 39.2B per token
- Architecture
- MixtralForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2024-04-16
- License
- Apache 2.0
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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 15.3 GB (at full 66K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run WizardLM 2 8x22B?
No — WizardLM 2 8x22B requires at least 39.4 GB at IQ2_XXS, 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 IQ2_XXS at 39.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run WizardLM 2 8x22B on a Mac?
Yes — Mac Studio M5 Max (48 GB) and 55 other Macs can run WizardLM 2 8x22B, the smallest at IQ2_XXS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 85.1 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio (M3 Ultra, 96GB).
Can I run WizardLM 2 8x22B locally?
Yes — WizardLM 2 8x22B can run locally on consumer hardware. 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 = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 23.7 GB active ÷ (8000 × 0.65) = 4.56 ms, plus 56 layers × 0.055 ms = 3.08 ms, so 1000 ÷ 7.64 ms = ~131 tok/s
Estimated speed at Q4_K_M (85.1 GB)
Real-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 (IQ2_XXS) is 38.67 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?
30 devices with unified memory can run WizardLM 2 8x22B at Q4_K_M (85.1 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (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.