SSyncDev

Llama-3-Blama-8B

SyncDev model directory · Profile updated Nov 17, 2026

Compare with another model

Llama-3-Blama-8B is Ai2's byte-level retrofit of Llama 3 8B, released to show the Bolmo byteification method works beyond Ai2's own Olmo models.

Key specifications

Specification score
4.8
License
llama3

The specification score summarizes recorded features and limits. It is not a benchmark result.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Text input

Produces

  • Text output

Capabilities

Open weights

What is Llama-3-Blama-8B?

Llama-3-Blama-8B exists to prove a point. Ai2's Bolmo method converts a conventional subword language model into one that reads and writes raw bytes, and until recently it had only been demonstrated on Ai2's own Olmo models. Retrofitting Meta's Llama 3 8B, a model trained by somebody else with a different recipe, shows the technique transfers. Ai2 released it on 7 October 2026 alongside a Qwen-based twin, when the Bolmo research was published in Nature. Ai2 also calls it simply "Blama 8B".

Why convert a model you could just use?

Because the tokeniser is a fixed vocabulary, every subword model inherits its blind spots: awkward splits of rare words, inconsistent whitespace, weak handling of unfamiliar scripts and exact strings. A byte-level model sees every character. Training one from scratch costs a fortune. Byteification gets there with a comparatively short additional run, keeping most of what the original network learned.

The catch is quality. Byteified checkpoints come close to their source models but do not fully match them, and the research community is still working out the trade-off between byte-level efficiency and character-level understanding.

Blama versus Bwen

Llama-3-Blama-8B Bwen 8B
Source model Llama 3 8B Qwen3-8B
Licence Llama 3 licence Apache 2.0
Released 7 October 2026 7 October 2026
Ai2's verdict Close to its source Strongest byteified model so far

The licence is the practical difference. Blama inherits Meta's Llama 3 terms (tagged llama3), not Apache 2.0, so the usual Llama 3 conditions on use and attribution apply. If you want permissive terms and the stronger scores, the Qwen-based Bwen 8B is the better default. Blama is more interesting if your existing stack, prompts or fine-tuning data are built around Llama 3.

Stage 1 checkpoints

As with the other retrofits, Ai2 published Stage 1 versions in which the original Llama network stays frozen while the new byte components train. They are a cheaper starting point if you want to run your own byteification experiments rather than use the finished model.

Practical notes

  • Weights: allenai/Llama-3-Blama-8B, part of Ai2's Bolmo collection.
  • Size: 8B parameters, text only.
  • Read the repository's loading instructions before you start. Its Qwen-based sibling needs custom modelling code (trust_remote_code) and counts generation length in bytes, and you should assume nothing about this one until you have checked.
  • No hosted API; this is a research release, not an assistant.
  • The repository was created in late August, about six weeks before Ai2 made the release public; we use the public release date.

Testing the retrofit

The cleanest experiment is a pair comparison: the original Llama 3 8B against the byte version, on the same prompts. Use one set that stresses characters (misspellings, base64 strings, transliteration) and one ordinary set (reading comprehension, short QA). The first shows what you gain, the second what you lose. For context on the wider Llama lineage see Llama 3.1 405B and the Meta Llama provider page; Ai2's other work is on the Ai2 provider page.

How to evaluate Llama-3-Blama-8B

Compare the model on the work you need to complete.

Tasks and inputs

Llama-3-Blama-8B is listed for Fill-mask, Text generation. It accepts text and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.

Choosing a deployment

The weights are downloadable under llama3. Check runtime support and size the complete model and working context for your expected concurrency.

Frequently asked questions

A byte-level version of Llama 3 8B produced with Ai2's Bolmo byteification method, released to show the technique works on non-Ai2 models.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

Microsoft

Aion 1.0 Instruct 2.3B

Aion 1.0 Instruct 2.3B is Microsoft's MIT-licensed on-device small language model and Phi Silica successor for Windows, with a 32K context.

32.77K context

Google

Gemini 4 Neon

Gemini 4 Neon is Google's mid-tier Gemini 4 model for complex coding and analysis, sitting between Hydrogen and Carbon at $3/$15 per 1M tokens.

1.05M context

OpenAI

GPT-6.2 Astra

GPT-6.2 Astra is OpenAI's November 2026 flagship for hard professional, scientific and agentic work, at $8/$40 per million tokens with a 1.05M context.

1.05M context

OpenAI

GPT-6.2 Sol

GPT-6.2 Sol is OpenAI's everyday model for coding, agents and writing: $2/$10 per million tokens, 1.05M context, released 17 November 2026.

1.05M context

Alibaba

Qwen4 Max

Qwen4 Max (qwen4-max) is Alibaba's first Qwen4-generation flagship: 1M-token context, text, image and video input, thinking on by default, $1.50/$4.50 per 1M.

1M context

Sarvam

Sarvam-105B-1711

Sarvam-105B-1711 is a refreshed open post-train of Sarvam's 105B MoE, tuned for tool calling, instruction following, agents and Indian languages.

— context