Devstral 2 123B Instruct 2512 — Hardware Requirements & GPU Compatibility
Chat
Devstral 2 123B Instruct 2512 is Mistral AI's large agentic coding model for software engineering tasks such as exploring codebases, editing multiple files, and running autonomous coding agents. Released as an FP8-quantized checkpoint of a roughly 125-billion-parameter dense model, it is a direct step up from the smaller Devstral Small line and pairs with Mistral's own Vibe CLI as well as third-party scaffolds like OpenHands and Claude Code. It scores 72.2% on SWE-Bench Verified, 61.3% on SWE-Bench Multilingual, and 32.6% on Terminal-Bench 2, competitive with or ahead of several much larger open models. At this size it needs a multi-GPU workstation even when quantized. Context length is 262,144 tokens. It is released under a Modified MIT License that blocks companies with over $20 million in monthly consolidated revenue from using it without a separate commercial license from Mistral AI. It was published in November 2025.
12.8K downloads
341 likesSpecifications
- Publisher
- Mistral AI
- Family
- Mistral
- Parameters
- 125.0B
- Architecture
- Ministral3ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2025-11-28
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Devstral 2 123B Instruct 2512 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 54.2 GB | 147.9 GB | 53.14 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 55.7 GB | 149.5 GB | 54.70 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 62.0 GB | 155.7 GB | 60.95 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 63.5 GB | 157.3 GB | 62.51 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 76.0 GB | 169.8 GB | 75.02 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 90.1 GB | 183.9 GB | 89.08 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 104.2 GB | 197.9 GB | 103.15 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 126.1 GB | 219.8 GB | 125.03 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Devstral 2 123B Instruct 2512?
Q4_K_M · 76.0 GBDevstral 2 123B Instruct 2512 (Q4_K_M) requires 76.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 99+ GB is recommended. Using the full 262K context window can add up to 93.8 GB, bringing total usage to 169.8 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Devstral 2 123B Instruct 2512?
Q4_K_M · 76.0 GB18 devices with unified memory can run Devstral 2 123B Instruct 2512, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, NVIDIA Jetson AGX Thor Developer Kit.
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightWhere to Download Devstral 2 123B Instruct 2512
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Devstral 2 123B Instruct 2512 need?
Devstral 2 123B Instruct 2512 requires 76.0 GB of VRAM at Q4_K_M, or 251.1 GB at BF16. Full 262K context adds up to 93.8 GB (169.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 125.0B × 4.8 bits ÷ 8 = 75 GB
KV Cache + Overhead ≈ 1 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 94.8 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M76.0 GBQ4_K_M + full context169.8 GB- Can NVIDIA GeForce RTX 5090 run Devstral 2 123B Instruct 2512?
No — Devstral 2 123B Instruct 2512 requires at least 35.4 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for Devstral 2 123B Instruct 2512?
For Devstral 2 123B Instruct 2512, Q4_K_M (76.0 GB) offers the best balance of quality and VRAM usage. Q4_K_L (77.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 35.4 GB.
VRAM requirement by quantization
IQ2_XXS35.4 GBQ2_K54.2 GBQ3_K_L65.1 GBQ4_K_M ★76.0 GBQ4_K_L77.6 GBBF16251.1 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Devstral 2 123B Instruct 2512 on a Mac?
Devstral 2 123B Instruct 2512 requires at least 35.4 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 Devstral 2 123B Instruct 2512 locally?
Yes — Devstral 2 123B Instruct 2512 can run locally on consumer hardware. At Q4_K_M quantization it needs 76.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Devstral 2 123B Instruct 2512?
At Q4_K_M, Devstral 2 123B Instruct 2512 can reach ~63 tok/s on AMD Instinct MI350X. 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 ÷ 76.0 × 0.65 = ~68 tok/s
Estimated speed at Q4_K_M (76.0 GB)
~68 tok/s~68 tok/s~63 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Devstral 2 123B Instruct 2512?
At Q4_K_M, the download is about 75.02 GB. The full-precision BF16 version is 250.05 GB. The smallest option (IQ2_XXS) is 34.38 GB.
- Which GPUs can run Devstral 2 123B Instruct 2512?
No single consumer GPU has enough VRAM to run Devstral 2 123B Instruct 2512 at Q4_K_M (76.0 GB). Multi-GPU or professional hardware is required.
- Which devices can run Devstral 2 123B Instruct 2512?
19 devices with unified memory can run Devstral 2 123B Instruct 2512 at Q4_K_M (76.0 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), 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.