Up to date
unsloth Llama 3.1 Community License out 2 years ago
8.03B parameters, text in, text out, 128K tokens of context. 1 provider serves it.
Verified 2026-10-26 07:27 UTC Rank #530 in LLMs · score 75.5 method v1 Sources 3 Downloads 30d 188k · #253 of 619 tracked
Picked by rule from 25 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 2 picks above, plus these 23. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
| # | Cheapest live row | In /1M | Out /1M | Context | Quant | Seen |
|---|---|---|---|---|---|---|
| 1 | Featherless | — | — | — | — | Oct 26 |
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Served by 1 API provider; heavily run locally (80 quantized builds); a big base for builders (2,345 fine-tunes, adapters and merges).
Top Spaces running it: John6666/joy-caption-pre-alpha-mod ♥ 65 · rahul7star/ai-toolkit ♥ 10 · MegaTronX/joy-caption-pre-alpha-mod ♥ 5 · lucyknada/hf-model-get-chat-template ♥ 4
Weights only, an estimate: leave room for the KV cache. Method
About 4.8 GB at INT4, 9.6 GB at FP8, 19 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2024-07-23), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.
2,425 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | LlamaForCausalLM |
| Model type | llama |
| Dtype | bfloat16 |
| Params by dtype | BF16: 8,030,261,248 |
| Size band | M |
| MoE | no |
| Context length | 131,072 (config.json max_position_embeddings) |
| Languages | en |
| License | Llama 3.1 Community License (llama3.1) |
| Hub snapshot | 2026-10-26 |
vLLM: supported · LlamaForCausalLM · 4b1c04e76fe9ac3ca8b7e541dd423e7d5f38dc60SGLang: supported · LlamaForCausalLM · 60d941293e3af27a12c6eb64e2c3e2e1a17f100f
vLLM registry (4b1c04e76fe9ac3ca8b7e541dd423e7d5f38dc60) · SGLang registry (60d941293e3af27a12c6eb64e2c3e2e1a17f100f) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for Meta-Llama-3.1-8B-Instruct: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 19 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 9.6 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 4.8 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
Base model: meta-llama/Llama-3.1-8B-Instruct
quantized: 80adapter: 541finetune: 1,765merge: 39
| Date | Commit | SHA |
|---|---|---|
| 2025-02-15 | Add files using upload-large-folder tool | a285619 |
| 2025-02-02 | Add files using upload-large-folder tool | 28e14b5 |
| 2024-11-22 | Update README.md | da09a33 |
| 2024-09-03 | Upload tokenizer | 4a5a8d9 |
| 2024-09-03 | Upload config | 62b4abd |
| 2024-09-03 | Upload config | e23cc57 |
| 2024-08-20 | Upload tokenizer | 6dfabbc |
| 2024-08-20 | Upload config | 38d94f7 |
| 2024-08-20 | Upload config | 1119532 |
| 2024-08-16 | Upload tokenizer | 4c9aa50 |
| 2024-08-16 | Upload config | 6298b94 |
| 2024-08-16 | Upload config | 3f6ff05 |
| 2024-08-15 | Upload tokenizer | a58182b |
| 2024-08-15 | Upload config | 39d4065 |
| 2024-08-15 | Upload config | 06476c0 |
| 2024-08-13 | Upload tokenizer | 76db79b |
| 2024-08-13 | Upload config | c984e4c |
| 2024-08-13 | Upload config | 1964578 |
| 2024-08-09 | Upload tokenizer | 04ebeec |
| 2024-08-09 | Upload config | b1e3fae |
| 2024-08-09 | Upload config | 4c6f03f |
| 2024-08-08 | Upload tokenizer | f073dd6 |
| 2024-08-08 | Upload config | 20b4ce3 |
| 2024-08-08 | Upload config | 4b2f37b |
| 2024-08-07 | Upload tokenizer | 1959b3d |
| 2024-08-07 | Upload config | 59a397a |
| 2024-08-07 | Upload config | ec0724a |
| 2024-08-07 | Upload tokenizer | 315fc37 |
| 2024-08-07 | Upload config | b91f11a |
| 2024-08-07 | Upload config | a5483c8 |
Hosted endpoints observed for Meta-Llama-3.1-8B-Instruct, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| Featherless hf | unsloth/Meta-Llama-3.1-8B-Instruct | — | — | — | — | — | — | — | live | 2026-10-26 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency.
Hub snapshot: 2026-10-26 · HF API: 2026-10-26 07:21 UTC · Providers: 2026-10-26 07:26 UTC · Articles: 2026-10-26 07:27 UTC · Summary: 2026-10-07 15:11 UTC · Last verified 2026-10-26 07:27 UTC
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
