cognitivecomputations_Dolphin3.0-R1-Mistral-24B GGUF size and VRAM requirements

Reasoning Engine ⬇ 14,571 ❤ 86
Parameters23.57B
Context32,768

cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF is a large reasoning-focused model focused on complex reasoning & stem. With approximately 23.57 billion parameters, it balances local hardware requirements with reasoning and generation fidelity. It is built on the llama architecture with a native context window of up to 32,768 tokens. The model is primarily recommended for multi-step logic deductions, mathematical problem solving, chain-of-thought analysis, and scientific research. Packaged in the standard GGUF container, it runs fully offline in Ollama, LM Studio, and llama.cpp.

Under the hood it uses 40 transformer layers, a hidden size of 5,120, 32 attention heads. It uses grouped-query attention (32 query heads sharing 8 key/value heads), which already trims KV-cache memory compared with full multi-head attention.

To run bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF locally at a 4,096-token context, its quantized versions need between 7.52 GB (IQ2_XXS, lowest quality) and 89.25 GB (F32, highest quality) of memory, weights plus KV cache and a system margin included. Context length drives that memory directly: at 4,096 tokens the KV cache for cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF is about 0.62 GB, rising to roughly 5.0 GB at its full 32,768-token context. Shorter prompts free up memory for a higher-quality quantization.

For most users the best balance is IQ2_XXS, needing about 7.52 GB. That means bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF fits entirely in the VRAM of an 8 GB GPU or larger, running fully on the GPU.

Available GGUF quantizations for bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF include IQ2_XXS, IQ2_XS, IQ2_S, IQ2_M, Q2_K, Q2_K_L, IQ3_XS, Q3_K_S, IQ3_M, Q3_K_M, Q3_K_L, IQ4_XS, Q3_K_XL, IQ4_NL, Q4_0, Q4_K_S, Q4_K_M, Q4_K_L, Q4_1, Q5_K_S, Q5_K_M, Q5_K_L, Q6_K, Q6_K_L, Q8_0, F32. The model supports a native context length of up to 32,768 tokens; a longer context grows the KV cache and the memory needed.

→ Guide: How much VRAM do you need?

Reasoning Engine

Recommended Use Cases & Local Setup

Complex Reasoning & STEM

Ideal for: Multi-step logic deductions, mathematical problem solving, chain-of-thought analysis, and scientific research.

LM Studio

Native support for collapsing and viewing multi-step <think> reasoning tokens

Open WebUI

Rich web interface supporting reasoning models with system prompts disabled

Ollama

High-throughput local API backend

Prompting & Sampling Tip: Set temperature between 0.5 and 0.7. Do not enforce strict response schemas or system prompts that restrict the model's internal reasoning tokens.

GGUF file size and memory by quantization

Compare real GGUF weight sizes, estimated KV cache and total memory for Q4, Q5, Q8 and every quantization published in this repository.

Quant.Bits QualityWeights KVTotal Speed~Verdict
IQ2_XXS 2.22 Very low 6.1 GB 0.62 GB 7.52 GB 65.6 t/s Fits in VRAM
IQ2_XS 2.45 Very low 6.71 GB 0.62 GB 8.14 GB 7.4 t/s Offload
IQ2_S 2.54 Very low 6.96 GB 0.62 GB 8.39 GB 7.2 t/s Offload
IQ2_M 2.75 Low 7.56 GB 0.62 GB 8.98 GB 6.6 t/s Offload
Q2_K 3.02 Low 8.28 GB 0.62 GB 9.7 GB 6.0 t/s Offload
Q2_K_L 3.24 Low 8.89 GB 0.62 GB 10.32 GB 5.6 t/s Offload
IQ3_XS 3.36 Fair 9.23 GB 0.62 GB 10.65 GB 5.4 t/s Offload
Q3_K_S 3.53 Fair 9.69 GB 0.62 GB 11.11 GB 5.2 t/s Offload
IQ3_M 3.61 Fair 9.92 GB 0.62 GB 11.34 GB 5.0 t/s Offload
Q3_K_M 3.89 Fair 10.69 GB 0.62 GB 12.11 GB 4.7 t/s Offload
Q3_K_L 4.21 Good 11.55 GB 0.62 GB 12.97 GB 4.3 t/s Offload
IQ4_XS 4.33 Good 11.88 GB 0.62 GB 13.31 GB 4.2 t/s Offload
Q3_K_XL 4.41 Good 12.1 GB 0.62 GB 13.52 GB 4.1 t/s Offload
IQ4_NL 4.57 Good 12.54 GB 0.62 GB 13.97 GB 4.0 t/s Offload
Q4_0 4.58 Good 12.57 GB 0.62 GB 13.99 GB 4.0 t/s Offload
Q4_K_S 4.6 Good 12.62 GB 0.62 GB 14.04 GB 4.0 t/s Offload
Q4_K_M 4.86 Good 13.35 GB 0.62 GB 14.77 GB 3.7 t/s Offload
Q4_K_L 5.03 Very good 13.81 GB 0.62 GB 15.24 GB 3.6 t/s Offload
Q4_1 5.05 Very good 13.85 GB 0.62 GB 15.28 GB 3.6 t/s Offload
Q5_K_S 5.53 Very good 15.18 GB 0.62 GB 16.61 GB 3.3 t/s Offload
Q5_K_M 5.69 Very good 15.61 GB 0.62 GB 17.04 GB 3.2 t/s Offload
Q5_K_L 5.83 Very good 16.0 GB 0.62 GB 17.42 GB 3.1 t/s Offload
Q6_K 6.57 Excellent 18.02 GB 0.62 GB 19.44 GB 2.8 t/s Offload
Q6_K_L 6.68 Excellent 18.32 GB 0.62 GB 19.75 GB 2.7 t/s Offload
Q8_0 8.5 Excellent 23.33 GB 0.62 GB 24.76 GB Insufficient
F32 32.0 Excellent 87.82 GB 0.62 GB 89.25 GB Insufficient

KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.

Frequently asked questions

What kind of model is bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF?

bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF is a reasoning-focused model with 23.57 billion parameters, based on the llama architecture. It is distributed as GGUF files for local inference.

How much VRAM do you need to run bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF?

You need about 7.52 GB of VRAM to run bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF entirely on the GPU using the IQ2_XXS quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.

Can I run bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF on an 8 GB GPU?

Yes. With 8 GB of VRAM you can run bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF fully on the GPU using IQ2_XXS (about 7.52 GB).

Can I run bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF on a 16 GB GPU?

Yes. With 16 GB of VRAM you can run bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF fully on the GPU using Q4_1 (about 15.28 GB).

Can I run bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF on a 24 GB GPU?

Yes. With 24 GB of VRAM you can run bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF fully on the GPU using Q6_K_L (about 19.75 GB).

What context length does bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF support?

bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF supports a native context length of up to 32,768 tokens. A longer context grows the KV cache, so it increases the memory needed to run the model.

What is the best quantization for bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF?

For bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF, a strong default is Q4_K_M, which needs about 14.77 GB and keeps most of the quality while roughly halving the memory versus 8-bit. With VRAM to spare, Q5_K_M or Q6_K add a little more quality; if you are tight on memory, a smaller quantization still runs. Pick the highest quantization that fits your VRAM.