ModelTape
All modelsNew releasesRankingsRuns on my GPUOpen the app →
ModelTape / Models / Ministral 3 8B
Mistral · open-weights

Ministral 3 8B

Ministral 3 8B is an open-weights language model from Mistral, released December 2, 2025. It has 8.9B parameters (dense). The context window is 256K tokens. API price: $0.15 input / $0.15 output per million tokens.

Today, we announce Mistral 3, the next generation of Mistral models. Mistral 3 includes three state-of-the-art small, dense models (14B, 8B, and 3B) and Mistral Large 3 – our most capable model to date – a sparse mixture-of-experts trained with 41B active and 675B total parameters.

Check it against your own PC →

Lab
Mistral
Released
December 2, 2025
Weights
Open apache-2.0
Parameters
8.9B dense
Context
256K
Price / M tokens
$0.15 / $0.15 in / out
Epoch ECI
not yet rated

Can you run Ministral 3 8B locally?

The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, split GPU / CPU, roughly 5 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.

GPU memoryVerdictBest quantVRAMRAMtok/s
6 GB VRAMRuns, slowlyQ6_K (≈ lossless)5.2 GB5.0 GB~5
8 GB VRAMRuns, slowlyQ6_K (≈ lossless)7.2 GB3.0 GB~8
12 GB VRAMRuns on GPUQ6_K (≈ lossless)10.2 GB–~29
16 GB VRAMRuns on GPUQ6_K (≈ lossless)10.2 GB–~39
24 GB VRAMRuns on GPUQ6_K (≈ lossless)10.2 GB–~71
32 GB VRAMRuns on GPUQ6_K (≈ lossless)10.2 GB–~130

Ready-made quantizations on Hugging Face: Mungert/Ministral-3-8B-Reasoning-2512-GGUF · mradermacher/Ministral-3-8B-Base-2512-i1-GGUF · mradermacher/Ministral-3-8B-Base-2512-GGUF · AISafety-Student/Ministral-3-8B-Reasoning-2512-heretic_GGUF · mlx-community/Ministral-3-8B-Instruct-2512-4bit · mlx-community/Ministral-3-8B-Reasoning-2512-4bit

Benchmark results

Epoch AI has not published results for Ministral 3 8B yet. New models are usually evaluated within days to weeks.

Links

Announcement · Hugging Face: mistralai/Ministral-3-8B-Base-2512

More from Mistral

Mistral Large 4 · Mistral Large 4 Preview · Mistral Large 4 1T A52B · Leanstral 1.5 · Mistral Medium 3.5 · Mistral Small 4 · Devstral Small 2 · Devstral 2

Data updated Thu, 12 Nov 2026 09:42 UTC. Benchmarks, Capabilities Index and model announcements: Epoch AI, “Capabilities & benchmarking” and “Data on AI models” (CC BY 4.0); category scores are ModelTape's own fit on Epoch's results. Releases and prices: models.dev (MIT). Sizes and quantizations: Hugging Face. “Runs on” figures are estimates from model size, quantization and memory bandwidth (±30–50%).
Live app · All models · New releases · Rankings · 6 GB · 8 GB · 12 GB · 16 GB · 24 GB · 32 GB · Legal notice (Impressum) · Privacy