Mistral Small 4 119B 2603 — Hardware Requirements & GPU Compatibility
Chat
Mistral Small 4 119B is Mistral AI's mixture-of-experts model with 119 billion total parameters and about 6.5 billion active per token, using 128 experts with 4 active. It unifies the company's Instruct, Reasoning (formerly Magistral) and Devstral lines in one checkpoint, accepts text and image input, and lets users set reasoning effort per request. The card positions it for chat assistants, coding, agentic work with native function calling, and document understanding. Even with few active parameters, all 119 billion weights must be held in memory, so it needs multi-GPU or a large unified-memory machine even when quantized. The card states a 256k-token context window. It is released under the Apache 2.0 license, permitting commercial and non-commercial use. Released as version 2603 (March 2026), it is billed as a successor to Mistral Small 3, with the card reporting a 40 percent cut in end-to-end completion time in a latency-optimized setup.
54.7K downloads
430 likesSpecifications
- Publisher
- Mistral AI
- Family
- Mistral
- Parameters
- 119.4B
- Architecture
- Mistral3ForConditionalGeneration
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-01-23
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Mistral Small 4 119B 2603 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 52.3 GB | 669.5 GB | 50.75 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 53.8 GB | 671.0 GB | 52.24 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 59.7 GB | 677.0 GB | 58.21 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 61.2 GB | 678.5 GB | 59.70 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 73.2 GB | 690.4 GB | 71.64 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 86.6 GB | 703.9 GB | 85.07 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 100.0 GB | 717.3 GB | 98.51 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 120.9 GB | 738.2 GB | 119.40 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Mistral Small 4 119B 2603?
Q4_K_M · 73.2 GBMistral Small 4 119B 2603 (Q4_K_M) requires 73.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 96+ GB is recommended. Using the full 1049K context window can add up to 617.3 GB, bringing total usage to 690.4 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Mistral Small 4 119B 2603?
Q4_K_M · 73.2 GB18 devices with unified memory can run Mistral Small 4 119B 2603, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightWhere to Download Mistral Small 4 119B 2603
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 Mistral Small 4 119B 2603 need?
Mistral Small 4 119B 2603 requires 73.2 GB of VRAM at Q4_K_M, or 240.3 GB at BF16. Full 1049K context adds up to 617.3 GB (690.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 119.4B × 4.8 bits ÷ 8 = 71.6 GB
KV Cache + Overhead ≈ 1.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 618.8 GB (at full 1049K context)
VRAM usage by quantization
Q4_K_M73.2 GBQ4_K_M + full context690.4 GB- Can NVIDIA GeForce RTX 5090 run Mistral Small 4 119B 2603?
No — Mistral Small 4 119B 2603 requires at least 34.3 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for Mistral Small 4 119B 2603?
For Mistral Small 4 119B 2603, Q4_K_M (73.2 GB) offers the best balance of quality and VRAM usage. Q4_K_L (74.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 34.3 GB.
VRAM requirement by quantization
IQ2_XXS34.3 GBQ2_K52.3 GBIQ4_XS65.7 GBQ4_K_M ★73.2 GBQ5_183.6 GBBF16240.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Mistral Small 4 119B 2603 on a Mac?
Mistral Small 4 119B 2603 requires at least 34.3 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 Mistral Small 4 119B 2603 locally?
Yes — Mistral Small 4 119B 2603 can run locally on consumer hardware. At Q4_K_M quantization it needs 73.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Mistral Small 4 119B 2603?
At Q4_K_M, Mistral Small 4 119B 2603 can reach ~123 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 ÷ 73.2 × 0.65 = ~356 tok/s
Estimated speed at Q4_K_M (73.2 GB)
~356 tok/s~356 tok/s~300 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Mistral Small 4 119B 2603?
At Q4_K_M, the download is about 71.64 GB. The full-precision BF16 version is 238.80 GB. The smallest option (IQ2_XXS) is 32.84 GB.
- Which GPUs can run Mistral Small 4 119B 2603?
No single consumer GPU has enough VRAM to run Mistral Small 4 119B 2603 at Q4_K_M (73.2 GB). Multi-GPU or professional hardware is required.
- Which devices can run Mistral Small 4 119B 2603?
19 devices with unified memory can run Mistral Small 4 119B 2603 at Q4_K_M (73.2 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.