Up to date
Models › TinyLlama-v1.0 family
TinyLlama Apache 2.0 out 3 years ago
1.10B parameters, text in, text out, 2K tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #162 in LLMs · score 91.8 method v1 Sources 3 Downloads 30d 964.4k · #116 of 619 tracked
Changed this week: 5 new quantized builds on the Hub (165 in all).2026-10-24
Picked by rule from 3 tracked pieces: the lab's own post, the most shared, a field report, the latest.
TinyLlama-1.1B-Chat-v1.0 is a 1.1 billion parameter model trained on datasets including Cerebras/SlimPajama-627B and released in early 2024.
The 2 picks above, plus these 1. 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 25 |
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 (165 quantized builds); a big base for builders (2,222 fine-tunes, adapters and merges).
Top Spaces running it: Vokturz/can-it-run-llm ♥ 1,053 · pliny-the-prompter/obliteratus ♥ 621 · cvachet/pdf-chatbot ♥ 382 · AI-nthusiast/cognitive-proxy ♥ 140
Weights only, an estimate: leave room for the KV cache. Method
About 0.7 GB at INT4, 1.3 GB at FP8, 2.6 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 (2023-12-30), amber triangles are 1 dated article (each links to it), grey ticks are repo commits.
2,387 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: 1,100,048,384 |
| Size band | S |
| MoE | no |
| Context length | 2,048 (config.json max_position_embeddings) |
| Languages | en |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · LlamaForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · LlamaForCausalLM · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · 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 TinyLlama-1.1B-Chat-v1.0: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 2.6 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 1.3 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.7 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 165adapter: 1,605finetune: 585merge: 32
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF | quantized | GGUF | — | — | apache-2.0 | TheBloke | 238 | 2.4M |
| TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ | quantized | GPTQ | 1.10B | S | apache-2.0 | TheBloke | 14 | 1.7M |
| RedHatAI/TinyLlama-1.1B-Chat-v1.0-marlin | quantized | — | 260M | S | — | RedHatAI | 2 | 160.9k |
| barissglc/tinyllama-tarot-v1 | adapter | — | — | — | apache-2.0 | barissglc | 8 | 107.8k |
| givyboy/TinyLlama-1.1B-Chat-v1.0-mental-health-conversational | adapter | — | — | — | apache-2.0 | givyboy | 9 | 104.9k |
| snshrivas10/sft-tiny-chatbot | adapter | — | — | — | apache-2.0 | snshrivas10 | 0 | 100k |
| TheBloke/TinyLlama-1.1B-Chat-v1.0-AWQ | quantized | AWQ | 1.10B | S | apache-2.0 | TheBloke | 6 | 64.4k |
| OpenVINO/TinyLlama-1.1B-Chat-v1.0-int4-ov | quantized | int4 | — | — | apache-2.0 | OpenVINO | 3 | 45.1k |
| Edentns/DataVortexTL-1.1B-v0.1 | finetune | — | 1.10B | S | cc-by-nc-sa-4.0 | Edentns | 0 | 44.6k |
| RedHatAI/TinyLlama-1.1B-Chat-v1.0-pruned2.4 | finetune | — | — | — | apache-2.0 | RedHatAI | 2 | 43.4k |
| second-state/TinyLlama-1.1B-Chat-v1.0-GGUF | quantized | GGUF | — | — | apache-2.0 | second-state | 1 | 33k |
| alexredna/TinyLlama-1.1B-Chat-v1.0-reasoning-v2 | finetune | — | 1.10B | S | apache-2.0 | alexredna | 1 | 31.9k |
| Xenova/TinyLlama-1.1B-Chat-v1.0 | quantized | — | — | — | — | Xenova | 8 | 27.2k |
| OpenVINO/TinyLlama-1.1B-Chat-v1.0-int8-ov | quantized | int8 | — | — | apache-2.0 | OpenVINO | 1 | 24.6k |
| mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f16_1-MLC | quantized | — | — | — | — | mlc-ai | 0 | 21.6k |
| s3nh/TinyLLama-4x1.1B-MoE | merge | — | 3.38B | M | mit | s3nh | 7 | 20.4k |
| litert-community/TinyLlama-1.1B-Chat-v1.0 | finetune | — | — | — | apache-2.0 | litert-community | 5 | 18.9k |
| andrijdavid/tinyllama-dare | merge | — | 1.10B | S | apache-2.0 | andrijdavid | 1 | 13.4k |
| ShieldX/manovyadh-1.1B-v1-chat | finetune | — | 1.10B | S | apache-2.0 | ShieldX | 1 | 13k |
| frankenmerger/MiniLlama-1.8b-Chat-v0.1 | finetune | — | 1.89B | S | apache-2.0 | frankenmerger | 2 | 11.3k |
| hieupt/TinyLlama-1.1B-Chat-v1.0-Q4_K_M-GGUF | quantized | GGUF | — | — | apache-2.0 | hieupt | 2 | 9.8k |
| h4rz3rk4s3/TinyParlaMintLlama-1.1B | finetune | — | 1.10B | S | apache-2.0 | h4rz3rk4s3 | 0 | 9.1k |
| MaziyarPanahi/TinyLlama-1.1B-Chat-v1.0-GGUF | quantized | GGUF | — | — | apache-2.0 | MaziyarPanahi | 2 | 8.9k |
| davanstrien/TinyLlama-1.1B-Chat-v1.0-intel-dpo | finetune | — | 1.10B | S | apache-2.0 | davanstrien | 0 | 8.3k |
| QuantFactory/minecraft-GGUF | quantized | GGUF | — | — | cc | QuantFactory | 4 | 7.9k |
| lxcorp/lambda-1v-1B | finetune | — | 1.10B | S | mit | lxcorp | 1 | 7.8k |
| alexredna/Tukan-1.1B-Chat-reasoning-sft-COLA | finetune | — | 1.10B | S | apache-2.0 | alexredna | 0 | 7.8k |
| mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC | quantized | — | — | — | — | mlc-ai | 0 | 6.9k |
| mradermacher/TinyLlama-1.1B-Chat-v1.0-i1-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 1 | 6.7k |
| mewaeltsegay/desta_1b | finetune | — | 1.10B | S | apache-2.0 | mewaeltsegay | 0 | 6.5k |
| pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF | quantized | GGUF | — | — | apache-2.0 | pbatra | 0 | 6.4k |
| arif-butt/tinyllama-trl-merged | adapter | — | 1.10B | S | apache-2.0 | arif-butt | 0 | 5.8k |
| arif-butt/tinyllama-peft-merged | adapter | — | 1.10B | S | apache-2.0 | arif-butt | 0 | 5.8k |
| arif-butt/tinyllama-unsloth-merged | adapter | — | 1.10B | S | apache-2.0 | arif-butt | 0 | 5.7k |
| h4rz3rk4s3/TinyPoliticaLlama-1.1B | finetune | — | 1.10B | S | apache-2.0 | h4rz3rk4s3 | 0 | 5.6k |
| h4rz3rk4s3/TinyNewsLlama-1.1B | finetune | — | 1.10B | S | apache-2.0 | h4rz3rk4s3 | 0 | 5.3k |
| raidhon/coven_tiny_1.1b_32k_orpo_alpha | finetune | — | 1.10B | S | apache-2.0 | raidhon | 2 | 5k |
| selinazarzour/healthgpt-tinyllama | quantized | — | 1.13B | S | apache-2.0 | selinazarzour | 0 | 5.1k |
| Sanjay002/tinyllama-mental-health-finetuned | finetune | — | 1.10B | S | mit | Sanjay002 | 3 | 4.6k |
| premrajreddy/tinyllama-1.1b-home-llm | finetune | GGUF | 1.10B | S | apache-2.0 | premrajreddy | 0 | 4.5k |
| Date | Commit | SHA |
|---|---|---|
| 2024-03-17 | Update examples in README to be compatible with soon-to-come ChatWidget (#23) | fe8a4ea |
| 2024-01-12 | Update README.md (#18) | 77e2396 |
| 2024-01-02 | Add example prompt (#4) | de253fa |
| 2024-01-02 | Update README.md | b3cbbe1 |
| 2024-01-02 | Upload tokenizer.model | af8e934 |
| 2023-12-31 | Update README.md | 44ea18e |
| 2023-12-31 | Update README.md | 2fef611 |
| 2023-12-31 | Delete all_results.json | 36b9dab |
| 2023-12-31 | Delete train_results.json | 6302cb1 |
| 2023-12-31 | Delete training_args.bin | ac66911 |
| 2023-12-31 | Delete trainer_state.json | d912882 |
| 2023-12-31 | Delete runs | 11c20b6 |
| 2023-12-31 | Update config.json | 26d45f2 |
| 2023-12-30 | End of training | f14d07e |
| 2023-12-30 | Model save | 5243d15 |
| 2023-12-30 | initial commit | eb800a9 |
Hosted endpoints observed for TinyLlama-1.1B-Chat-v1.0, 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 | TinyLlama/TinyLlama-1.1B-Chat-v1.0 | — | — | — | — | — | — | — | live | 2026-10-25 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:35 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:03 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
