How much memory do I need to run aura-fleet-gguf-part3 (Q4_K_M)?

The file size is 4.68 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 6.23 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.

Does aura-fleet-gguf-part3 run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?

8 GB: up to Q4_K_M (est. 6.46 GB); 12 GB: up to Q4_K_M (est. 6.46 GB); 16 GB: up to Q4_K_M (est. 6.46 GB); 24 GB: up to Q4_K_M (est. 6.46 GB) (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).

What is the command to run aura-fleet-gguf-part3 with Ollama?

Run "ollama run hf.co/engmauriciodias33/aura-fleet-gguf-part3:Q4_K_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.

engmauriciodias33

aura-fleet-gguf-part3

Parameters: 7.6B
Max context length: 32,768
Architecture: qwen2

Memory needed to run Q4_K_M at 8K tokens

6.23 GB Estimated

File size 4.68 GB Measured

VRAM it fits in (rough guide)

8 GB fits
12 GB fits
16 GB fits
24 GB fits
32 GB fits
48 GB fits

See devices and models for 6 GB

Macs cap how much memory the GPU can use, so leave headroom in unified memory.

Data as of Nov 3, 2026

About aura-fleet-gguf-part3

aura-fleet-gguf-part3 is a model published in GGUF format. GGUF files are published by engmauriciodias33/aura-fleet-gguf-part3. It has about 7.6B parameters, the qwen2 architecture, a maximum context length of 32,768 tokens (values written in the GGUF).

There is one quantization, Q4_K_M, with a file size of 4.68 GB (actual size on Hugging Face).

Running Q4_K_M (4.68 GB) with an 8,192-token context needs an estimated 6.23 GB of memory, and an estimated 7.64 GB at 32,768 tokens. For 8,192 tokens, a GPU with 6 GB or more of VRAM (such as Arc A380, GeForce RTX 4050 Laptop GPU), or a Mac with 6 GB or more of unified memory, is a rough guide (macOS caps how much memory the GPU can use, so leave some headroom).

File size and estimated memory per quantization

Up to 8 GB
Up to 16 GB
Up to 24 GB
Up to 48 GB
Up to 128 GB
More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization	Quality guide	KLD (no imatrix)	KLD (imatrix)	Size (Llama-3-8B)
Q8_0	Nearly identical	0.0014	-	7.96 GiB
Q6_K	Very small	0.0055	-	6.14 GiB
Q5_K_M	Very small	0.0108	-	5.33 GiB
Q5_K_S	Small	0.0166	-	5.21 GiB
Q5_1	Small	0.0180	-	5.65 GiB
Q5_0	Small	0.0222	-	5.21 GiB
Q4_K_M	Small	0.0313	0.0282	4.58 GiB
Q4_K_S	Medium	0.0431	0.0320	4.37 GiB
IQ4_NL	Small	-	0.0357	4.35 GiB
IQ4_XS	Small	-	0.0363	4.14 GiB
Q4_1	Medium	0.0717	-	4.78 GiB
Q4_0	Medium	0.0719	-	4.34 GiB
Q3_K_L	Medium	0.0872	0.0731	4.03 GiB
Q3_K_M	Medium	0.1019	0.0844	3.74 GiB
IQ3_M	Medium	-	0.1025	3.53 GiB
IQ3_S	Medium	-	0.1113	3.42 GiB
IQ3_XS	Large	-	0.1387	3.28 GiB
IQ3_XXS	Large	-	0.1836	3.05 GiB
Q3_K_S	Large	0.2282	0.1998	3.41 GiB
IQ2_M	Large	-	0.3260	2.74 GiB
Q2_K	Very large	0.4451	0.3322	2.96 GiB
Q2_K_S	Very large	-	0.4034	2.96 GiB
IQ2_S	Very large	-	0.4392	2.56 GiB
IQ2_XS	Very large	-	0.5463	2.43 GiB
IQ2_XXS	Very large	-	0.8120	2.24 GiB
IQ1_M	Very large	-	1.3931	2.01 GiB
IQ1_S	Very large	-	2.2546	1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

engmauriciodias33/aura-fleet-gguf-part3

Published by the original developer About this label

Last checked: Nov 3, 2026

Architecture: qwen2; Supported before llama.cpp b4409
Parameters: 7.6B
Max context length: 32,768

File size and memory per quantization for aura-fleet-gguf-part3 (engmauriciodias33/aura-fleet-gguf-part3)
Quantization	File size Measured	Quality guide	4,096	8,192	16,384	32,768 max
Q4_K_M aura_expert_813_room_temp_hydride_superconductor_wire_architecture_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_99_orbital_tether_momentum_exchange_launcher_control_loop_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_833_room_temp_hydride_superconductor_wire_optimization_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_826_hypersonic_scramjet_magnetohydrodynamic_optimization_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_693_room_temp_hydride_superconductor_wire_telemetry_fusion_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_256_quantum_gravimetry_subterranean_mineral_mapper_autonomous_agent_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_262_sodium_sugar_hard_carbon_cathode_cryptographic_proof_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_293_room_temp_hydride_superconductor_wire_telemetry_fusion_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_827_autonomous_depin_byzantine_mesh_optimization_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_87_autonomous_depin_byzantine_mesh_control_loop_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_269_aya_64kb_progressive_tensor_pager_cryptographic_proof_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_681_silicon_photonics_sub_angstrom_telemetry_fusion_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_255_deep_sea_cobalt_crust_autonomous_harvester_autonomous_agent_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_835_deep_sea_cobalt_crust_autonomous_harvester_optimization_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_674_bci_32ch_eegnet_motor_imagery_decoder_cryptographic_proof_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_95_deep_sea_cobalt_crust_autonomous_harvester_control_loop_q4_k_m	4.68 GB	Small	5.99 GB	6.23 GB	6.70 GB	7.64 GB
Q4_K_M aura_expert_657_mrna_neoantigen_personalized_oncology_autonomous_agent_q4_k_m	4.92 GB	Small	6.23 GB	6.46 GB	6.93 GB	7.87 GB
Q4_K_M aura_expert_831_synthetic_cyanobacteria_co2_to_butanol_optimization_q4_k_m	4.92 GB	Small	6.23 GB	6.46 GB	6.93 GB	7.87 GB
Q4_K_M aura_expert_680_anti_lawfare_sovereign_jurisprudence_ai_cryptographic_proof_q4_k_m	4.92 GB	Small	6.23 GB	6.46 GB	6.93 GB	7.87 GB
Q4_K_M aura_expert_837_mrna_neoantigen_personalized_oncology_optimization_q4_k_m	4.92 GB	Small	6.23 GB	6.46 GB	6.93 GB	7.87 GB
Q4_K_M aura_expert_91_synthetic_cyanobacteria_co2_to_butanol_control_loop_q4_k_m	4.92 GB	Small	6.23 GB	6.46 GB	6.93 GB	7.87 GB
Q4_K_M aura_expert_671_synthetic_cyanobacteria_co2_to_butanol_cryptographic_proof_q4_k_m	4.92 GB	Small	6.23 GB	6.46 GB	6.93 GB	7.87 GB

Ollama  ollama run hf.co/engmauriciodias33/aura-fleet-gguf-part3:Q4_K_M

llama.cpp  llama-server -hf engmauriciodias33/aura-fleet-gguf-part3:Q4_K_M

Generation speed on common GPUs and Macs (estimated)

A rough guide to how fast Q4_K_M (4.68 GB) generates text. Each token reads the model weights once, so the upper limit is memory bandwidth ÷ file size. The guide is 60–80% of that, where most published measurements fall.

Device	Memory bandwidth	Guide (tokens/s) Estimated	Upper limit
Arc A380 6 GB	186 GB/s	24–32	40
Arc A770M 16 GB	512 GB/s	66–87	109
GeForce RTX 5090 32 GB	1,792 GB/s	230–306	383
Apple M2 8 GB	100 GB/s	13–17	21
Apple M2 Pro 16 GB	200 GB/s	26–34	43
Apple M5 Ultra 96 GB	1,200 GB/s	154–205	256

Estimates only. Prompt processing speed (limited by compute) is not included. Longer contexts and offloading part of the model to the CPU make it slower. Macs are shown only when installed memory is at least 4/3 of what is needed. Devices without published bandwidth (some GeForce cards, etc.) are not shown.

How to run

Example commands using Q4_K_M. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/engmauriciodias33/aura-fleet-gguf-part3:Q4_K_M

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf engmauriciodias33/aura-fleet-gguf-part3:Q4_K_M

LM Studio

Paste engmauriciodias33/aura-fleet-gguf-part3 into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run aura-fleet-gguf-part3 (Q4_K_M)?: The file size is 4.68 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 6.23 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
Does aura-fleet-gguf-part3 run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?: 8 GB: up to Q4_K_M (est. 6.46 GB); 12 GB: up to Q4_K_M (est. 6.46 GB); 16 GB: up to Q4_K_M (est. 6.46 GB); 24 GB: up to Q4_K_M (est. 6.46 GB) (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
What is the command to run aura-fleet-gguf-part3 with Ollama?: Run "ollama run hf.co/engmauriciodias33/aura-fleet-gguf-part3:Q4_K_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.