MN 12B Mag Mell R1 — Hardware Requirements & GPU Compatibility
ChatReasoning
MN 12B Mag Mell R1 is a 12.2B-parameter open language model from inflatebot. It supports a context window of up to 1,024,000 tokens. At Q4_K_M it needs about 8.07 GB of VRAM — see which GPUs and Macs can run it below.
59.4K downloads
239 likesSpecifications
- Publisher
- inflatebot
- Parameters
- 12.2B
- Architecture
- MistralForCausalLM
- Context Length
- 1,024,000 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2025-04-03
Get Started
HuggingFace
How Much VRAM Does MN 12B Mag Mell R1 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 5.9 GB | 215.2 GB | 5.21 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 6.1 GB | 215.4 GB | 5.36 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 6.7 GB | 216.0 GB | 5.97 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 6.8 GB | 216.1 GB | 6.12 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 8.1 GB | 217.4 GB | 7.35 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 9.4 GB | 218.7 GB | 8.73 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 10.8 GB | 220.1 GB | 10.10 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 13.0 GB | 222.3 GB | 12.25 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run MN 12B Mag Mell R1?
Q4_K_M · 8.1 GBMN 12B Mag Mell R1 (Q4_K_M) requires 8.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 11+ GB is recommended. Using the full 1024K context window can add up to 209.3 GB, bringing total usage to 217.4 GB. 28 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run MN 12B Mag Mell R1?
Q4_K_M · 8.1 GB27 devices with unified memory can run MN 12B Mag Mell R1, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Derivatives (4)
Frequently Asked Questions
- How much VRAM does MN 12B Mag Mell R1 need?
MN 12B Mag Mell R1 requires 8.1 GB of VRAM at Q4_K_M, or 13.0 GB at Q8_0. Full 1024K context adds up to 209.3 GB (217.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 12.2B × 4.8 bits ÷ 8 = 7.3 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 210.1 GB (at full 1024K context)
VRAM usage by quantization
Q4_K_M8.1 GBQ4_K_M + full context217.4 GB- What's the best quantization for MN 12B Mag Mell R1?
For MN 12B Mag Mell R1, Q4_K_M (8.1 GB) offers the best balance of quality and VRAM usage. Q4_K_L (8.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 4.1 GB.
VRAM requirement by quantization
IQ2_XXS4.1 GBIQ3_S5.9 GBQ3_K_L7.0 GBQ4_K_M ★8.1 GBQ4_K_L8.2 GBQ8_013.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run MN 12B Mag Mell R1 on a Mac?
MN 12B Mag Mell R1 requires at least 4.1 GB at IQ2_XXS, 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 MN 12B Mag Mell R1 locally?
Yes — MN 12B Mag Mell R1 can run locally on consumer hardware. At Q4_K_M quantization it needs 8.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is MN 12B Mag Mell R1?
At Q4_K_M, MN 12B Mag Mell R1 can reach ~361 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~81 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 ÷ 8.1 × 0.55 = ~361 tok/s
Estimated speed at Q4_K_M (8.1 GB)
~361 tok/s~81 tok/s~270 tok/s~223 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of MN 12B Mag Mell R1?
At Q4_K_M, the download is about 7.35 GB. The full-precision Q8_0 version is 12.25 GB. The smallest option (IQ2_XXS) is 3.37 GB.
- Which GPUs can run MN 12B Mag Mell R1?
28 consumer GPUs can run MN 12B Mag Mell R1 at Q4_K_M (8.1 GB). Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 17 GPUs have plenty of headroom for comfortable inference.
- Which devices can run MN 12B Mag Mell R1?
27 devices with unified memory can run MN 12B Mag Mell R1 at Q4_K_M (8.1 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.