Public preview · figures are illustrative fixture data, attributed to their source · data to May 2025 · read-only
Model · Llama 3.1 · July 2024 Live · Hugging Face

Llama 3.1 8B

A 8 billion-parameterHow many numbers the model learned during training — the usual rough measure of its size. dense model from Meta. 8B, 70B and 405B models with 128K context.

Size
8.03Bdense
Memory to run
~6 GBsmallest, 8K ctx
Context
128Ktokens
License
PermissiveLlama 3.1 Community License; Apache License 2.0
Updated
18 Sept 2026

Which version to use

Other sizes in Llama 3.1: Llama 3.1 70B

Where it runs

Best-fitting version on each reference system, at an 8K contextHow much text the model can consider at once, counted in tokens — roughly ¾ of a word each..

Runs well 12

Slowly (CPU or offload) 1

Too large 0

None of the reference systems.

Benchmarks

Each benchmarkA fixed set of questions every model is given, so their scores can be compared on the same task. is developer-reported; prompts and settings differ between labs. Bars are relative to the best open result.

BenchmarkLlama 3.1 8B Instruct
Benchmark GPQA DiamondAccuracy
30.4src
Benchmark HumanEvalpass@1
72.6src
Benchmark IFEvalStrict prompt accuracy
80.4src
Benchmark MMLU-ProAccuracy
48.3src

developer reported

Variants & downloads

Each variant is a separate set of weights. Expand one for its downloads: quantizationStoring each of the model’s numbers with fewer bits, so the file is smaller and needs less memory. trades a little quality for a much smaller file, and the memory column adds the working memoryExtra space the model needs while it answers. It grows with the length of the conversation, on top of the file itself. a conversation needs on top.

Variant Llama 3.1 8Bbase · Meta · 1 download · Llama 3.1 Community LicenseRestricted
What it is
Pretrained foundation weights — a starting point for fine-tuning, not for chat.
Publisher
Meta
License
Llama 3.1 Community License · commercial use restricted
Released
23 Jul 2024

Contributions are not open yet, so there is nothing here from members.

QuantizationFormatBitsDownloadMemory @ 8KPublisher
Download BF16nativesafetensors1615.0 GiB~17.1 GiBMetameta-llama/Llama-3.1-8B
Variant Llama 3.1 8B Instructinstruct · Meta · 5 downloads · Llama 3.1 Community LicenseRestricted
What it is
Tuned to follow instructions and hold a conversation. The usual choice.
Publisher
Meta
License
Llama 3.1 Community License · commercial use restricted
Released
23 Jul 2024

Contributions are not open yet, so there is nothing here from members.

QuantizationFormatBitsDownloadMemory @ 8KPublisher
Download BF16nativesafetensors1615.0 GiB~17.1 GiBMetameta-llama/Llama-3.1-8B-Instruct
Download Q8_0legacy ggufgguf8.57.9 GiB~9.8 GiBLM Studio Communitylmstudio-community/Llama-3.1-8B-Instruct-GGUF
Download FP8fp8safetensors8.18.5 GiB~10.3 GiBRedHatAIRedHatAI/Meta-Llama-3.1-8B-Instruct-FP8
Download Q4_K_Mk quantgguf4.894.6 GiB~6.3 GiBLM Studio Communitylmstudio-community/Llama-3.1-8B-Instruct-GGUF
Download MLX 4-bitmlxmlx4.54.2 GiB~5.9 GiBMLX Communitymlx-community/Llama-3.1-8B-Instruct-4bit
Variant Hermesfine tune · dedsecisback2026 (third-party) · 0 downloadsLicense unknown
What it is
A community or third-party fine-tune of another variant.
Publisher
dedsecisback2026
License
Unknown
Released
21 Aug 2026

Contributions are not open yet, so there is nothing here from members.

No downloadable artifacts recorded.

Variant Hermes 3 Llama 3.1 8Bfine tune · NousResearch (third-party) · 3 downloads · Llama 3.1 Community LicenseRestricted
What it is
A community or third-party fine-tune of another variant.
Publisher
NousResearch
License
Llama 3.1 Community License · commercial use restricted
Released
28 Jul 2024

Contributions are not open yet, so there is nothing here from members.

QuantizationFormatBitsDownloadMemory @ 8KPublisher
Download Q8_0legacy ggufgguf8.58.0 GiB~9.8 GiBNousResearchNousResearch/Hermes-3-Llama-3.1-8B-GGUF
Download Q6_Kk quantgguf6.566.1 GiB~7.9 GiBNousResearchNousResearch/Hermes-3-Llama-3.1-8B-GGUF
Download Q4_K_Mk quantgguf4.894.6 GiB~6.3 GiBNousResearchNousResearch/Hermes-3-Llama-3.1-8B-GGUF
Variant neurologist 7B instructfine tune · mainbrains (third-party) · 0 downloads · Apache License 2.0Permissive
What it is
A community or third-party fine-tune of another variant.
Publisher
mainbrains
License
Apache License 2.0 · commercial use allowed
Released
20 Aug 2026

Contributions are not open yet, so there is nothing here from members.

No downloadable artifacts recorded.

Variant solana nvidia trading factory 8Bfine tune · solanaclawd (third-party) · 0 downloads · Apache License 2.0Permissive
What it is
A community or third-party fine-tune of another variant.
Publisher
solanaclawd
License
Apache License 2.0 · commercial use allowed
Released
6 Sept 2026

Contributions are not open yet, so there is nothing here from members.

No downloadable artifacts recorded.

Architecture detailsLayers, attention and KV cache geometry
Parameters
8.03B
Active / token
All (dense)
Architecture
Dense
Layers
32
Attention heads
32
KV heads
8
Head dim
128
KV cache @ 8K (fp16)
1.00 GiB
Max context
131,072 tokens

Measured performance

Throughput on specific systems and runtimes, with the source of each measurement.

QuantizationSystemRuntimeContextMeasurementsSource
Llama 3.1 8B Instruct Q4_K_M (LM Studio Community)CPU-only Ryzen 9 7950X (128 GB DDR5)llama.cppcpu · b46004K
92 tok/s · Prompt processing (512)
12.4 tok/s · Generation (128)
Mutinai illustrative fixtures
Llama 3.1 8B Instruct Q4_K_M (LM Studio Community)MacBook Pro M3 Max 64 GBllama.cppmetal · b46004K
760 tok/s · Prompt processing (512)
54 tok/s · Generation (128)
Mutinai illustrative fixtures
Llama 3.1 8B Instruct Q4_K_M (LM Studio Community)RTX 4090 workstation (64 GB DDR5)llama.cppcuda · b46004K
12,100 tok/s · Prompt processing (512)
128 tok/s · Generation (128)
Mutinai illustrative fixtures
Llama 3.1 8B Instruct Q4_K_M (LM Studio Community)RX 7900 XTX desktop (64 GB DDR5)llama.cpprocm · b46004K
3,050 tok/s · Prompt processing (512)
94 tok/s · Generation (128)
Mutinai illustrative fixtures

Community results

Contributions are not open yet, so there is nothing here from members.

Reviews

Contributions are not open yet, so there is nothing here from members.

Lineage

How this model’s variants relate to each other and to other models.

VariantLlama 3.1 8B base
VariantHermes 3 Llama 3.1 8B fine-tuned from Llama 3.1 8B
VariantLlama 3.1 8B Instruct instruct

Sources & history

Sources

  • Hugging Face (fixture) (illustrative fixture, 1 record, 13 Sept 2026)
  • Hugging Face Hub (live source, 1 record, 13 Sept 2026)
  • Mutinai illustrative fixtures (illustrative fixture, 1 record, 13 Sept 2026)

External identifiers

Field history

  • license = "llama3.1" Hugging Face Hub (current)
  • license = "llama3.1" Hugging Face (fixture)
  • base = "NousResearch/Hermes-3-Llama-3.1-8B" Hugging Face Hub (current)
  • derivation = "fine_tune" Hugging Face Hub (current)
  • license = null Hugging Face Hub (current)
  • name = "Hermes" Hugging Face Hub (current)
  • base = "meta-llama/Llama-3.1-8B" Hugging Face (fixture) (current)
  • derivation = "fine_tune" Hugging Face (fixture) (current)
  • license = "llama3" Hugging Face (fixture) (current)
  • name = "Hermes 3 Llama 3.1 8B" Hugging Face (fixture) (current)
  • base = "NousResearch/Hermes-3-Llama-3.1-8B" Hugging Face Hub (current)
  • derivation = "fine_tune" Hugging Face Hub (current)

Timeline

  1. Hermes 3 fine-tunes of Llama 3.1 released
  2. Meta releases Llama 3.1 (8B, 70B, 405B)