Pollux Judge 32B — Hardware Requirements & GPU Compatibility
Chat
Pollux Judge 32B is a 32.8B-parameter open language model from ai-forever. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 20.49 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs on 24 GB (Q4_K_M · ~32 tok/s · 8K)Macs from 24 GB (Q4_K_M · ~11 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Pollux Judge 32B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve ai-forever/pollux-judge-32b --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX PRO 4500 (32 GB) (7 GB headroom) · Q4_K_M
- Generation speed
- ~28 tok/s
- generation speed
- Cost per 1M output tokens
- $3.33
- per 1M output tokens
How Much VRAM Does Pollux Judge 32B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 14.8 GB | 22.8 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~44 tok/s | |
| 16.8 GB | 24.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 16K context · ~39 tok/s | |
| 20.5 GB | 28.5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 8K context · ~32 tok/s | |
| 24.2 GB | 32.2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 27.9 GB | |
| 27.9 GB | 35.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 31.6 GB | |
| 33.6 GB | 41.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 37.4 GB | |
| 66.4 GB | 74.4 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 70.1 GB |
Selected Q4_K_M
4-bit medium quantization24.3GBat 16K context
- Weights
- 19.7 GB
- KV cache
- 4.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · fits up to 8K context · ~32 tok/s
≥50 tok/s needs ≥1.57 TB/s · RTX 5090 ~57
Which Hardware Can Run Pollux Judge 32B?
Q4_K_M · 20.5 GBPollux Judge 32B (Q4_K_M) requires 20.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 27+ GB is recommended. Using the full 33K context window can add up to 8.1 GB, bringing total usage to 28.6 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Pollux Judge 32B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit Q2_K (18.5 GB)
1 GPU
RX 7900 XT~33Simulate output on RX 7900 XT32–40 GB
fits · 7.8 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~57Simulate output on RTX 5090M5 Max36 GB~16Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~4Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.7 35B A3BOpenBMB | — | 22.1 GB | ~169 | same size |
| NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA | — | 19.3 GB | ~197 | same size |
| Agents A1InternScience | — | 21.5 GB | ~171 | same size |
| Ornith 1.0 35BDeep Reinforce | — | 21.5 GB | ~171 | same size |
| EXAONE 4.5 33BLGAI-EXAONE | — | 23.9 GB | ~33 | same size |
| Gemma 4 31BGoogle | — | 22.6 GB | ~31 | same size |
Specifications
- Publisher
- ai-forever
- Parameters
- 32.8B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 151,665
- Release Date
- 2025-06-05
- License
- MIT
Frequently Asked Questions
How much VRAM does Pollux Judge 32B need?
Pollux Judge 32B requires 20.5 GB of VRAM at Q4_K_M, or 66.4 GB at BF16. Full 33K context adds up to 8.1 GB (28.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32.8B × 4.8 bits ÷ 8 = 19.7 GB
KV Cache + Overhead ≈ 0.8 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 ≈ 8.9 GB (at full 33K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Pollux Judge 32B?
Yes, at Q4_K_M (20.5 GB) or lower. Higher quantizations like Q5_K_M (24.2 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Pollux Judge 32B?
For Pollux Judge 32B, Q4_K_M (20.5 GB) offers the best balance of quality and VRAM usage. Q5_K_M (24.2 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 14.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Pollux Judge 32B on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Pollux Judge 32B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 20.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run Pollux Judge 32B locally?
Yes — Pollux Judge 32B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Pollux Judge 32B?
At Q4_K_M, Pollux Judge 32B can reach ~234 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~32 tok/s. 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 ÷ 20.5 × 0.65 = ~254 tok/s
Estimated speed at Q4_K_M (20.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Pollux Judge 32B?
At Q4_K_M, the download is about 19.66 GB. The full-precision BF16 version is 65.52 GB. The smallest option (Q2_K) is 13.92 GB.
Which GPUs can run Pollux Judge 32B?
7 consumer GPUs can run Pollux Judge 32B at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Pollux Judge 32B?
122 devices with unified memory can run Pollux Judge 32B at Q4_K_M (20.5 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, 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.