Pollux 4B Judge — Hardware Requirements & GPU Compatibility
Chat
Pollux 4B Judge is a 4.0B-parameter open language model from ai-forever. It supports a context window of up to 40,960 tokens. At Q4_K_M it needs about 2.90 GB of VRAM — see which GPUs and Macs can run it below.
4.7K downloads
4 likesSpecifications
- Publisher
- ai-forever
- Parameters
- 4.0B
- Architecture
- Qwen3ForCausalLM
- Context Length
- 40,960 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-04-12
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Pollux 4B Judge Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 2.2 GB | 5.8 GB | 1.71 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 2.5 GB | 6.0 GB | 1.96 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 2.9 GB | 6.5 GB | 2.41 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 3.4 GB | 6.9 GB | 2.87 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 3.8 GB | 7.4 GB | 3.32 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 4.5 GB | 8.1 GB | 4.02 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 8.5 GB | 12.1 GB | 8.04 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 Pollux 4B Judge?
Q4_K_M · 2.9 GBPollux 4B Judge (Q4_K_M) requires 2.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 41K context window can add up to 3.6 GB, bringing total usage to 6.5 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Pollux 4B Judge?
Q4_K_M · 2.9 GB33 devices with unified memory can run Pollux 4B Judge, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Pollux 4B Judge need?
Pollux 4B Judge requires 2.9 GB of VRAM at Q4_K_M, or 8.5 GB at BF16. Full 41K context adds up to 3.6 GB (6.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 4.0B × 4.8 bits ÷ 8 = 2.4 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 4.1 GB (at full 41K context)
VRAM usage by quantization
Q4_K_M2.9 GBQ4_K_M + full context6.5 GB- What's the best quantization for Pollux 4B Judge?
For Pollux 4B Judge, Q4_K_M (2.9 GB) offers the best balance of quality and VRAM usage. Q5_K_M (3.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.2 GB.
VRAM requirement by quantization
Q2_K2.2 GBQ4_K_M ★2.9 GBQ5_K_M3.4 GBQ6_K3.8 GBQ8_04.5 GBBF168.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Pollux 4B Judge on a Mac?
Pollux 4B Judge requires at least 2.2 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 Pollux 4B Judge locally?
Yes — Pollux 4B Judge can run locally on consumer hardware. At Q4_K_M quantization it needs 2.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Pollux 4B Judge?
At Q4_K_M, Pollux 4B Judge can reach ~1005 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~226 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 2.9 × 0.55 = ~1005 tok/s
Estimated speed at Q4_K_M (2.9 GB)
~1005 tok/s~226 tok/s~751 tok/s~622 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Pollux 4B Judge?
At Q4_K_M, the download is about 2.41 GB. The full-precision BF16 version is 8.04 GB. The smallest option (Q2_K) is 1.71 GB.
- Which GPUs can run Pollux 4B Judge?
35 consumer GPUs can run Pollux 4B Judge at Q4_K_M (2.9 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Pollux 4B Judge?
33 devices with unified memory can run Pollux 4B Judge at Q4_K_M (2.9 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.