Llama3-ChatQA-1.5-8B

nvidia Llama 3 Community License out 2 years ago

8.03B parameters, text in, text out, 8K tokens of context. 1 provider serves it.

Verified 2026-10-25 Rank #469 in LLMs · score 77.3 method v1 Sources 3 Downloads 30d 11.8k · #498 of 619 tracked

Can I run it?4.8GB at INT4Estimatefits a 16 GB cardmethod

Can I use it?Llama 3 Community License'Built with Llama' attribution; >700M MAU clause; naming rule for derivativeslicence file2026-10-24

Do people use it?11.8kdownloads, 30 days#498 of 619 we track · below the median+1 likes, downloads −1% this week558 likesHugging Face2026-10-24

Worth reading

Picked by rule from 13 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Most discussed · 2,199 HN pts

Meta Llama 3

llama.meta.com 2024-04-18 2,199 HN pts · 923 comments 42 words about the Llama3 family family

Latest · 23 months ago

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders

The project trained a Sparse Autoencoder on 6.5 Billion activations from Llama 3.2-3B layer 23 over 10 epochs.

github.com 2024-11-21 579 HN pts · 99 comments 5.8k words about the Llama3 family family

13 best of 13 tracked

The 2 picks above, plus these 11. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

CodeLlama3 implemented from scratchgithub.com · 2024-05-19 · 1,041 HN pts
CodeShow HN: I built a free in-browser Llama 3 chatbot powered by WebGPUgithub.com · 2024-05-03 · 547 HN pts
Codellama-fs: A self-organizing file system with llama 3github.com · 2024-05-26 · 221 HN pts
CodeOllama v0.1.33 with Llama 3, Phi 3, and Qwen 110Bgithub.com · 2024-04-28 · 192 HN pts
ArticleLlama 3-V: Matching GPT4-V with a 100x smaller model and 500 dollarsaksh-garg.medium.com · 2024-05-28 · 459 HN pts
ArticleCost of self hosting Llama-3 8B-Instructblog.lytix.co · 2024-06-14 · 245 HN pts
ArticleLlama 3 implemented in pure NumPydocs.likejazz.com · 2024-05-16 · 476 HN pts
CodeDeepDive in everything of Llama3: revealing detailed insights and implementationgithub.com · 2025-02-21 · 222 HN pts
ArticleRun llama3 locally with 1M token contextollama.com · 2024-04-30
ArticleImplementing LLaMA3 in 100 Lines of Pure Jaxsaurabhalone.com · 2025-02-19
ArticleFine tune LLAMA3 on million scale dataset in consumer GPU using QLora, DeepSpeedmedium.com · 2024-04-25

Show all 11

Where to run it

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

All 1 provider →

Where it's used

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; 17 quantized builds for local use.

As a service1Featherless
On own hardware17quantized builds
Built on206 fine-tunes · 7 adapters · 7 merges
In apps17Hugging Face Spaces

Top Spaces running it: GenAICoder/MultiPDFChatbot ♥ 20 · perctrix/AI-Lawyer ♥ 8 · ulab-ai/RoutePilot ♥ 1

Will it fit?

Weights only, an estimate: leave room for the KV cache. Method

Fits a 16 GB card at INT4

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

The story so far

Weights, every dated article, and repo commits on one rail.

10 dated articles and 30 repo commits so far

Teal is the weights (2024-04-28), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.

What people built on it

37 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

37 derivatives on the Hub, led by 17 quantized

From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.

GGUF legraphista/Llama3-ChatQA-1.5-8B-IMat-GGUF for llama.cpp, Ollama, LM Studio 35.2k downloads AWQ solidrust/Llama3-ChatQA-1.5-8B-AWQ for vLLM, SGLang 83 downloads

All variants →

Reference

Everything else, folded: the full tables, every source.

Benchmarks

11 rows

Benchmarks 11 rows

measured third-party leaderboard rowauthor-reported number from the model card or eval files (11)No confidence intervals unless the source gave them; settings differ between rows, so compare within a benchmark, not across. Date = the benchmark's own date when it gives one, else when we read it.

Benchmark	Value	Setting / notes	Reported by	Date
author-reported Average (all)	55.17	ChatQA-1.5-8B	model author	2026-10-07
author-reported CoQA	76.46	ChatQA-1.5-8B	model author	2026-10-07
author-reported ConvFinQA	78.46	ChatQA-1.5-8B	model author	2026-10-07
author-reported DoQA	49.6	ChatQA-1.5-8B	model author	2026-10-07
author-reported Doc2Dial	39.33	ChatQA-1.5-8B	model author	2026-10-07
author-reported HybriDial*	65.76	ChatQA-1.5-8B	model author	2026-10-07
author-reported INSCIT	30.1	ChatQA-1.5-8B	model author	2026-10-07
author-reported QReCC	49.03	ChatQA-1.5-8B	model author	2026-10-07
author-reported QuAC	39.73	ChatQA-1.5-8B	model author	2026-10-07
author-reported SQA	73.28	ChatQA-1.5-8B	model author	2026-10-07
author-reported TopioCQA	49.96	ChatQA-1.5-8B	model author	2026-10-07

What the card says

2 cited sentences

Summary generated, cited

Llama3-ChatQA-1.5-8B is an 8.03B parameter text-generation model built on the Llama-3 base model.^[1]^[2] The model is designed for conversational question answering and retrieval-augmented generation.^[3]

parameters human
“built on top of [Llama-3 base model]”
“excels at conversational question answering (QA) and retr…”

Generated 2026-10-07 15:11 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.

Use-case evidence

2 use cases

What it is good at 2 use cases

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.

Facts

22 fields

Listed in LLMs

Facts

Llama3-ChatQA-1.5-8B has 8.03B parameters. (safetensors metadata, observed 2026-10-24)
Context length is 8,192 tokens (8K). (config.json max_position_embeddings, observed 2026-10-24)
License: Llama 3 Community License (friction: attribution). 'Built with Llama' attribution; >700M MAU clause; naming rule for derivatives. (license file, observed 2026-10-24)
Created 2024-04-28, last modified 2024-05-24. (HF API, observed 2026-10-24)

Pipeline tag	text-generation
Library	transformers
Architectures	LlamaForCausalLM
Model type	llama
Dtype	float16
Params by dtype	F32: 2,048 · F16: 8,030,261,248
Size band	M
MoE	no
Context length	8,192 (config.json max_position_embeddings)
Languages	en
Papers	arXiv:2401.10225
License	Llama 3 Community License (llama3)
Hub snapshot	2026-10-25

Servability

vLLM · SGLang

Servability

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.

Hardware fit

3 estimates

Hardware fit ESTIMATE

Weights-only memory for Llama3-ChatQA-1.5-8B: 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.

All variants

37 variants

Lineage

Original model Family: nvidia/Llama3 37 derivatives on the Hub

quantized: 17merge: 7finetune: 6adapter: 7

Top variants (37 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
legraphista/Llama3-ChatQA-1.5-8B-IMat-GGUF	quantized	GGUF	—	—	llama3	legraphista	1	35.2k
PrunaAI/nvidia-Llama3-ChatQA-1.5-8B-GGUF-smashed	quantized	GGUF	—	—	—	PrunaAI	0	30.5k
QuantFactory/NVIDIA-Llama3-ChatQA-1.5-8B-GGUF	quantized	GGUF	—	—	llama3	QuantFactory	2	18.3k
mradermacher/Llama3-ChatQA-1.5-8B-i1-GGUF	quantized	GGUF	—	—	llama3	mradermacher	1	17.3k
mradermacher/Llama3-ChatQA-1.5-8B-GGUF	quantized	GGUF	—	—	llama3	mradermacher	0	14.9k
lmstudio-community/Llama3-ChatQA-1.5-8B-GGUF	quantized	GGUF	—	—	llama3	lmstudio-community	6	10.6k
QuantFactory/Open-Insurance-LLM-Llama3-8B-GGUF	quantized	GGUF	—	—	llama3	QuantFactory	6	7.7k
QuantFactory/llama-3-nvidia-ChatQA-1.5-8B-GGUF	quantized	GGUF	—	—	llama3	QuantFactory	1	7.1k
QuantFactory/Llama3.1-ArrowSE-v0.4-GGUF	merge	GGUF	—	—	llama3	QuantFactory	1	6.5k
Kukedlc/NeuralMiLLaMa-8B-slerp	merge	—	8.03B	M	other	Kukedlc	0	5.2k
DataPilot/Llama3.1-ArrowSE-v0.4	merge	—	8.03B	M	llama3	DataPilot	14	3.6k
Raj-Maharajwala/Open-Insurance-LLM-Llama3-8B-GGUF	quantized	GGUF	—	—	llama3	Raj-Maharajwala	5	3.8k
Raj-Maharajwala/Open-Insurance-LLM-Llama3-8B	finetune	—	8.03B	M	llama3	Raj-Maharajwala	4	2.3k
tensorblock/Llama3-ChatQA-1.5-8B-GGUF	quantized	GGUF	—	—	llama3	tensorblock	0	2.3k
HlaH/Llama3-ChatQA-Critic-PubMedQA	adapter	—	—	—	—	HlaH	0	2k
narainp/Llama3-ChatQA-1.5-8B-Q4_K_M-GGUF	quantized	GGUF	—	—	llama3	narainp	0	1.3k
Tech-Meld/Llama3-ChatQA-1.5-8B-Q4_K_S-GGUF	quantized	GGUF	—	—	llama3	Tech-Meld	2	870
grimjim/llama-3-nvidia-ChatQA-1.5-8B	finetune	—	8.03B	M	llama3	grimjim	3	729
MahmoudMohamed/LLama3_nvidia_QA_4bit	quantized	—	8.25B	M	apache-2.0	MahmoudMohamed	0	557
omar-sala7/LLama3-chat-FCAIBylaw-v1	adapter	—	—	—	llama3	omar-sala7	0	363
Itandy/chatqa1.5_ir0.5_d1w_0.5mix1.0	finetune	—	—	—	apache-2.0	Itandy	1	275
rollend/Llama3-ChatQA-1.5-8B-Q4_K_M-GGUF	quantized	GGUF	—	—	llama3	rollend	0	268
Tech-Meld/Hajax_Chat_1.0	merge	—	7.24B	M	—	Tech-Meld	0	258
Kukedlc/MergedLlama-3-8B-MS-2	merge	—	8.03B	M	—	Kukedlc	0	243
kscommhit/Llama3-ChatQA-1.5-8B-Q8_0-GGUF	quantized	Q8_0	—	—	llama3	kscommhit	0	187
abdoy/llama3-8b-sft-qlora-re-travel-chat	adapter	—	—	—	llama3	abdoy	0	185
omar-sala7/LLama3-chat-FCAIBylaw-v3	adapter	—	—	—	llama3	omar-sala7	0	135
kevinkawchak/nvidia-Llama3-ChatQA-1.5-8B-Molecule16	finetune	—	8.03B	M	llama3	kevinkawchak	0	119
AnirudhJM24/Llama3-ChatQA-1.5-8B-Q4_K_M-GGUF	quantized	GGUF	—	—	llama3	AnirudhJM24	0	100
solidrust/Llama3-ChatQA-1.5-8B-AWQ	quantized	AWQ	8.03B	M	—	solidrust	0	83
cenfis/Llama_3_merge	merge	—	8.03B	M	—	cenfis	0	79
Kukedlc/MergedLlama-3-8B-DT-3	merge	—	8.03B	M	—	Kukedlc	0	69
Meforgers/Turkish-LLama3	adapter	—	—	—	apache-2.0	Meforgers	0	34
HlaH/Llama3-ChatQA-Retriever-PubMedQA	adapter	—	—	—	—	HlaH	0	29
HlaH/Llama3-ChatQA-Generator-PubMedQA	adapter	—	—	—	—	HlaH	0	25
Thirawarit/checkpoint	finetune	—	—	—	llama3	Thirawarit	0	0
Felladrin/mlc-q4f16-Llama3-ChatQA-1.5-8B	finetune	—	—	—	llama3	Felladrin	0	0

Repository changelog

30 commits

Repository changelog 30 commits

Date	Commit	SHA
2024-05-24	Update README.md	3b98162
2024-05-17	Update tokenizer_config.json	396e122
2024-05-17	Update tokenizer_config.json	cc4e81a
2024-05-16	Update README.md	d12f6fc
2024-05-16	Update README.md	747c8c2
2024-05-16	Update README.md	06a4252
2024-05-16	Update README.md	ab81972
2024-05-08	Update README.md	4647a16
2024-05-07	Delete pytorch_model.bin.index.json	2a579cf
2024-05-07	Delete pytorch_model-00002-of-00002.bin	995d832
2024-05-07	Delete pytorch_model-00001-of-00002.bin	93c4981
2024-05-07	Update README.md	61e9725
2024-05-06	Adding `safetensors` variant of this model (#12)	df565a1
2024-05-04	Update README.md	a9c07a3
2024-05-04	Update README.md	56f7d8d
2024-05-04	Update README.md	642e023
2024-05-04	Update README.md	c16edd1
2024-05-03	Update README.md	d7df686
2024-05-03	Update README.md	db48521
2024-05-02	Update README.md	9ddd1d9
2024-05-02	Update README.md	43929b2
2024-05-02	Update README.md	b7d8679
2024-05-02	Update tokenizer_config.json	dce28f0
2024-05-02	Update README.md	9ab80de
2024-05-02	Update README.md	0311c8a
2024-05-02	Update README.md	8f93ac5
2024-05-02	Update README.md	3c7506a
2024-05-01	Upload docs.json	48418b5
2024-04-30	Update README.md	f31392b
2024-04-29	Update README.md	61ef0e5

All providers

1 provider · 1 endpoint

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for Llama3-ChatQA-1.5-8B, 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	nvidia/Llama3-ChatQA-1.5-8B	—	—	—	—	—	—	—	live	2026-10-25

Articles and coverage

13 pieces

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.

Analysis10

Meta Llama 3

llama.meta.com2024-04-18HN front pageabout the Llama3 familyHN 2,199 pts · 923 comments42 words

Llama3 implemented from scratch

github.com2024-05-19authorityHN front pageabout the Llama3 familyHN 1,041 pts · 269 comments2,465 words

An educational implementation of Llama 3 performs the model one matrix multiplication at a time using tiktoken for tokenization. The architecture includes 32 transformer layers, 32 attention heads, and a rope_theta of 500000.0, loading weights directly from the official Meta file. Attention weights are bundled together to help parallelize attention head multiplication rather than to reduce computation.written, reviewed, cited

The implementation does not include a BPE tokenizer, requiring users to download an external library for tokenization.
The model configuration specifies a norm_eps value of 1e-05 to prevent division by zero during RMS normalization.
Key weight matrices are shared across four attention heads to reduce the total number of computations required.

Show HN: I built a free in-browser Llama 3 chatbot powered by WebGPU

github.com2024-05-03authorityHN front pageabout the Llama3 familyHN 547 pts · 139 comments233 words

Secret-llama is an entirely-in-browser LLM chatbot powered by the webllm inference engine that runs fully private without needing a server. It supports models like Llama 3 and Mistral, ranging in size from 600MB to 4.3GB, requiring WebGPU support. Users can try it directly online, while developers compile the React code using yarn build-and-preview.written, reviewed, cited

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders

github.com2024-11-21authorityHN front pageabout the Llama3 familyHN 579 pts · 99 comments5,768 words

The project trained a Sparse Autoencoder on 6.5 Billion activations from Llama 3.2-3B layer 23 over 10 epochs. Data capture processed 25 million sentences totaling 4TB of raw activation data compressed to 3.2TB.generated, cited

llama-fs: A self-organizing file system with llama 3

github.com2024-05-26authorityHN front pageabout the Llama3 familyHN 221 pts · 62 comments546 words

LlamaFS is a self-organizing file manager that automatically renames and organizes files based on content and conventions. It requires Python 3.10 or higher and runs in batch or watch modes, processing most operations in <500ms. The system uses Llama 3 via Groq or Ollama, serving the application locally on port 8000.written, reviewed, cited

Ollama v0.1.33 with Llama 3, Phi 3, and Qwen 110B

github.com2024-04-28authorityHN front pageabout the Llama3 familyHN 192 pts · 64 comments38 words

Llama 3-V: Matching GPT4-V with a 100x smaller model and 500 dollars

aksh-garg.medium.com2024-05-28HN front pageabout the Llama3 familyHN 459 pts · 77 comments

Cost of self hosting Llama-3 8B-Instruct

blog.lytix.co2024-06-14HN front pageabout the Llama3 familyHN 245 pts · 183 comments1,403 words

Llama 3 implemented in pure NumPy

docs.likejazz.com2024-05-16HN front pageabout the Llama3 familyHN 476 pts · 50 comments

DeepDive in everything of Llama3: revealing detailed insights and implementation

github.com2025-02-21authorityHN front pageabout the Llama3 familyHN 222 pts · 14 comments12,330 words

All coverage tracked for this model (13) — append-only, nothing is ever removed

Title	Source	Published	First seen	Signals
DeepDive in everything of Llama3: revealing detailed insights and implementation	github.com	2025-02-21	2026-10-07	hn
Implementing LLaMA3 in 100 Lines of Pure Jax	saurabhalone.com	2025-02-19	2026-10-07	hn
Show HN: Llama 3.2 Interpretability with Sparse Autoencoders	github.com	2024-11-21	2026-10-07	hn
Cost of self hosting Llama-3 8B-Instruct	blog.lytix.co	2024-06-14	2026-10-07	hn
Llama 3-V: Matching GPT4-V with a 100x smaller model and 500 dollars	aksh-garg.medium.com	2024-05-28	2026-10-07	hn
llama-fs: A self-organizing file system with llama 3	github.com	2024-05-26	2026-10-07	hn
Llama3 implemented from scratch	github.com	2024-05-19	2026-10-07	hn
Llama 3 implemented in pure NumPy	docs.likejazz.com	2024-05-16	2026-10-07	hn
Show HN: I built a free in-browser Llama 3 chatbot powered by WebGPU	github.com	2024-05-03	2026-10-07	hn
Run llama3 locally with 1M token context	ollama.com	2024-04-30	2026-10-07	hn
Ollama v0.1.33 with Llama 3, Phi 3, and Qwen 110B	github.com	2024-04-28	2026-10-07	hn
Fine tune LLAMA3 on million scale dataset in consumer GPU using QLora, DeepSpeed	medium.com	2024-04-25	2026-10-07	hn
Meta Llama 3	llama.meta.com	2024-04-18	2026-10-07	hn

Papers

1 paper

Papers 1

arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).

ChatQA: Surpassing GPT-4 on Conversational QA and RAG this model

Zihan Liu, Wei Ping, Rajarshi Roy +4 · 2024-01-18 · PDF · HF paper page (35 upvotes)

Similar models

3 models

Similar models

Llama-3.1-8B-Instruct · 8.03B
same size band (M), same task (text-generation), more providers
Qwen3-8B · 8.19B
same size band (M), same task (text-generation), more providers, permissive license
Meta-Llama-3-8B-Instruct · 8.03B
same size band (M), same task (text-generation), more providers

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:40 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:11 UTC · Last verified 2026-10-25

Follow Llama3-ChatQA-1.5-8B

Watch this model

/feeds/models/nvidia--Llama3-ChatQA-1.5-8B.xml(RSS 2.0) · every change to Llama3-ChatQA-1.5-8B
/feeds/families/nvidia--Llama3.xml(RSS 2.0) · every change across the Llama3 family

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.