Gollem V4 250M Pl — Hardware Requirements & GPU Compatibility
Chat
Gollem V4 250M Pl is a 250M-parameter open language model from SlayerLab. At BF16 it needs about 0.55 GB of VRAM — see which GPUs and Macs can run it below.
4.9K downloads
2 likesSpecifications
- Publisher
- SlayerLab
- Parameters
- 250M
- Vocabulary Size
- 32,000
- Release Date
- 2026-09-14
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Gollem V4 250M Pl Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 0.6 GB | — | 0.50 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 Gollem V4 250M Pl?
BF16 · 0.6 GBGollem V4 250M Pl (BF16) requires 0.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Gollem V4 250M Pl?
BF16 · 0.6 GB59 devices with unified memory can run Gollem V4 250M Pl, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomFrequently Asked Questions
- How much VRAM does Gollem V4 250M Pl need?
Gollem V4 250M Pl requires 0.6 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 250M × 16 bits ÷ 8 = 0.5 GB
KV Cache + Overhead ≈ 0.1 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF160.6 GB- Can I run Gollem V4 250M Pl on a Mac?
Gollem V4 250M Pl requires at least 0.6 GB at BF16, 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 Gollem V4 250M Pl locally?
Yes — Gollem V4 250M Pl can run locally on consumer hardware. At BF16 quantization it needs 0.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Gollem V4 250M Pl?
At BF16, Gollem V4 250M Pl can reach ~8727 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1191 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 ÷ 0.6 × 0.65 = ~9455 tok/s
Estimated speed at BF16 (0.6 GB)
~9455 tok/s~1191 tok/s~9455 tok/s~8727 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Gollem V4 250M Pl?
At BF16, the download is about 0.50 GB.
- Which GPUs can run Gollem V4 250M Pl?
52 consumer GPUs can run Gollem V4 250M Pl at BF16 (0.6 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Gollem V4 250M Pl?
59 devices with unified memory can run Gollem V4 250M Pl at BF16 (0.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.