Baguettotron — Hardware Requirements & GPU Compatibility
Chat
Baguettotron is a 321M-parameter open language model from PleIAs. It supports a context window of up to 4,096 tokens. At Q4_K_M it needs about 0.62 GB of VRAM — see which GPUs and Macs can run it below.
4.8K downloads
240 likesSpecifications
- Publisher
- PleIAs
- Parameters
- 321M
- Architecture
- LlamaForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 65,536
- Release Date
- 2025-11-10
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Baguettotron Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 0.6 GB | 0.7 GB | 0.14 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 0.6 GB | 0.7 GB | 0.16 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 0.6 GB | 0.7 GB | 0.19 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 0.7 GB | 0.8 GB | 0.23 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 0.7 GB | 0.8 GB | 0.26 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 0.8 GB | 0.9 GB | 0.32 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 1.1 GB | 1.2 GB | 0.64 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 Baguettotron?
Q4_K_M · 0.6 GBBaguettotron (Q4_K_M) 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. Using the full 4K context window can add up to 0.1 GB, bringing total usage to 0.7 GB. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Baguettotron?
Q4_K_M · 0.6 GB59 devices with unified memory can run Baguettotron, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomFrequently Asked Questions
- How much VRAM does Baguettotron need?
Baguettotron requires 0.6 GB of VRAM at Q4_K_M, or 1.1 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 321M × 4.8 bits ÷ 8 = 0.2 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 0.5 GB (at full 4K context)
VRAM usage by quantization
Q4_K_M0.6 GBQ4_K_M + full context0.7 GB- What's the best quantization for Baguettotron?
For Baguettotron, Q4_K_M (0.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.6 GB.
VRAM requirement by quantization
Q2_K0.6 GBQ4_K_M ★0.6 GBQ5_K_M0.7 GBQ6_K0.7 GBQ8_00.8 GBBF161.1 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Baguettotron on a Mac?
Baguettotron requires at least 0.6 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 Baguettotron locally?
Yes — Baguettotron can run locally on consumer hardware. At Q4_K_M quantization it needs 0.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Baguettotron?
At Q4_K_M, Baguettotron can reach ~7097 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1057 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 = ~8387 tok/s
Estimated speed at Q4_K_M (0.6 GB)
~8387 tok/s~1057 tok/s~8387 tok/s~7097 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Baguettotron?
At Q4_K_M, the download is about 0.19 GB. The full-precision BF16 version is 0.64 GB. The smallest option (Q2_K) is 0.14 GB.
- Which GPUs can run Baguettotron?
50 consumer GPUs can run Baguettotron at Q4_K_M (0.6 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 50 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Baguettotron?
59 devices with unified memory can run Baguettotron at Q4_K_M (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.