Dolphin Mistral 24B Venice Edition — Hardware Requirements & GPU Compatibility
Chat
Dolphin Mistral 24B Venice Edition is a 24.0B-parameter open language model from Cognitive Computations in the Phi family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 15.13 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs from 12 GB (IQ2_M · 16K)Best on 24 GB (Q4_K_M · ~43 tok/s · 32K)Macs from 16 GB (IQ2_M · ~16 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Dolphin Mistral 24B Venice Edition
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3090 (24 GB) (5 GB headroom) · Q4_K_M
- Generation speed
- ~40 tok/s
- generation speed
- Cost per 1M output tokens
- $1.37
- per 1M output tokens
How Much VRAM Does Dolphin Mistral 24B Venice Edition Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 10.9 GB | 17.2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 64K context · ~60 tok/s | |
| 11.2 GB | 17.5 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~58 tok/s | |
| 12.4 GB | 18.7 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~53 tok/s | |
| 12.7 GB | 19 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~52 tok/s | |
| 15.1 GB | 21.4 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~43 tok/s | |
| 17.8 GB | 24.1 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 16K context · ~37 tok/s | |
| 20.5 GB | 26.8 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 16K context · ~32 tok/s | |
| 24.7 GB | 31 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 27.7 GB |
Selected Q4_K_M
4-bit medium quantization18.1GBat 16K context
- Weights
- 14.4 GB
- KV cache
- 3.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 5.9 GB free · ~43 tok/s
≥50 tok/s needs ≥1.16 TB/s · RTX 5090 ~77
Which Hardware Can Run Dolphin Mistral 24B Venice Edition?
Q4_K_M · 15.1 GBDolphin Mistral 24B Venice Edition (Q4_K_M) requires 15.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 20+ GB is recommended. Using the full 131K context window can add up to 26.4 GB, bringing total usage to 41.5 GB. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080. 122 devices with unified memory can run Dolphin Mistral 24B Venice Edition, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 1.9 GB free · up to 16K ctx
1 GPU
RX 7900 XT~32Simulate output on RX 7900 XT32–40 GB
fits · 13.9 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~77Simulate output on RTX 5090M5 Max36 GB~21Simulate output on Mac Studio M5 Max (36 GB)M532 GB~7Simulate output on MacBook Air 13" M5 (32 GB)Orin~9Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~6Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Dolphin Mistral 24B Venice Edition
Phi family · 9 models →Similar models
5| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Magistral Small 2509Mistral AI | 85.6 | 18.1 GB | ~43 | same size |
| LFM2.5 24B A2BLiquid AI | — | 15 GB | ~221 | same size |
| Gemma 4 26B A4BGoogle | — | 16.5 GB | ~171 | same size |
| Ariarhymes-ai | — | 20.2 GB | ~168 | same size |
| EuroLLM 22B Instruct 2512utter-project | — | 17.5 GB | ~46 | same size |
Specifications
- Publisher
- Cognitive Computations
- Family
- Phi
- Parameters
- 24.0B
- Architecture
- Mistral3ForConditionalGeneration
- Context Length
- 131,072 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2025-06-12
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Dolphin Mistral 24B Venice Edition need?
Dolphin Mistral 24B Venice Edition requires 15.1 GB of VRAM at Q4_K_M, or 48.7 GB at BF16. Full 131K context adds up to 26.4 GB (41.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 24.0B × 4.8 bits ÷ 8 = 14.4 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 27.2 GB (at full 131K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Dolphin Mistral 24B Venice Edition?
Yes, at Q6_K (20.5 GB) or lower. Higher quantizations like Q8_0 (24.7 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Dolphin Mistral 24B Venice Edition?
For Dolphin Mistral 24B Venice Edition, Q4_K_M (15.1 GB) offers the best balance of quality and VRAM usage. Q4_K_L (15.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 7.3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Dolphin Mistral 24B Venice Edition on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Dolphin Mistral 24B Venice Edition, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 15.1 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Dolphin Mistral 24B Venice Edition locally?
Yes — Dolphin Mistral 24B Venice Edition can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Dolphin Mistral 24B Venice Edition?
At Q4_K_M, Dolphin Mistral 24B Venice Edition can reach ~317 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~43 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 ÷ 15.1 × 0.65 = ~344 tok/s
Estimated speed at Q4_K_M (15.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Dolphin Mistral 24B Venice Edition?
At Q4_K_M, the download is about 14.41 GB. The full-precision BF16 version is 48.02 GB. The smallest option (IQ2_XXS) is 6.60 GB.
Which GPUs can run Dolphin Mistral 24B Venice Edition?
26 consumer GPUs can run Dolphin Mistral 24B Venice Edition at Q4_K_M. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3090 Ti, AMD Radeon RX 6800. 7 GPUs have plenty of headroom for comfortable inference.
Which devices can run Dolphin Mistral 24B Venice Edition?
122 devices with unified memory can run Dolphin Mistral 24B Venice Edition at Q4_K_M (15.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, 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.