Up to date
codellama Llama 2 Community License out 3 years ago
6.74B parameters, text in, text out, 16K tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #496 in LLMs · score 76.6 method v1 Sources 3 Downloads 30d 334.8k · #207 of 619 tracked
Picked by rule from 12 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 2 picks above, plus these 10. 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; 41 quantized builds for local use; a big base for builders (634 fine-tunes, adapters and merges).
Top Spaces running it: Vokturz/can-it-run-llm ♥ 1,053 · KBaba7/Quant ♥ 51 · EvanTHU/MotionLLM ♥ 43 · FallnAI/Quantize-HF-Models ♥ 19
Weights only, an estimate: leave room for the KV cache. Method
About 4.0 GB at INT4, 8.1 GB at FP8, 16 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 (2023-08-24), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.
675 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: 6,738,546,688 |
| Size band | M |
| MoE | no |
| Context length | 16,384 (config.json max_position_embeddings) |
| Languages | code |
| Papers | arXiv:2308.12950 |
| License | Llama 2 Community License (llama2) |
| 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 CodeLlama-7b-hf: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 16 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 8.1 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 4.0 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 41adapter: 549finetune: 79merge: 6
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| TheBloke/CodeLlama-7B-GGUF | quantized | GGUF | — | — | llama2 | TheBloke | 135 | 206.9k |
| TheBloke/CodeLlama-7B-GPTQ | quantized | GPTQ | 6.74B | M | llama2 | TheBloke | 14 | 20.7k |
| mradermacher/CodeLlama-7b-hf-i1-GGUF | quantized | GGUF | — | — | llama2 | mradermacher | 0 | 14.4k |
| QuantFactory/MathCoder2-CodeLlama-7B-GGUF | quantized | GGUF | — | — | apache-2.0 | QuantFactory | 2 | 6k |
| mradermacher/CodeLlama-7b-hf-GGUF | quantized | GGUF | — | — | llama2 | mradermacher | 0 | 5.7k |
| TheBloke/CodeLlama-7B-AWQ | quantized | AWQ | 6.74B | M | llama2 | TheBloke | 6 | 5k |
| QuantFactory/CodeLlama-7b-hf-GGUF | quantized | GGUF | — | — | — | QuantFactory | 0 | 3.9k |
| pranav-pvnn/codellama-7b-python-ai-assistant-full-gguf | quantized | gguf | — | — | llama2 | pranav-pvnn | 3 | 2.7k |
| monsterapi/codellama7b_codealpaca20k | adapter | — | — | — | — | monsterapi | 2 | 2.6k |
| TheBloke/CodeLlama-7B-GGML | finetune | — | — | — | llama2 | TheBloke | 27 | 860 |
| allenai/codetulu-2-7b | finetune | — | — | — | — | allenai | 1 | 1.3k |
| Junjie-Ye/TL-CodeLLaMA-2 | finetune | — | — | — | apache-2.0 | Junjie-Ye | 1 | 1.1k |
| facebook/layerskip-codellama-7B | finetune | — | 6.74B | M | other | 6 | 809 | |
| aravind-kesiraju/codellama-7b-hf-sql | adapter | — | 6.85B | M | — | aravind-kesiraju | 0 | 978 |
| alphahg/CodeLlama-7b-hf-rust-finetune-GGUF | quantized | GGUF | — | — | llama2 | alphahg | 0 | 863 |
| MathGenie/MathCoder2-CodeLlama-7B | finetune | — | 6.74B | M | apache-2.0 | MathGenie | 5 | 597 |
| codys12/MergeLlama-7b | adapter | — | — | — | llama2 | codys12 | 2 | 668 |
| mlx-community/CodeLlama-7b-hf-4bit-mlx | quantized | -4bit | 6.74B | M | llama2 | mlx-community | 0 | 636 |
| philschmid/code-llama-7b-text-to-sql | adapter | — | — | — | llama2 | philschmid | 4 | 377 |
| maximuslee07/code-llama-7b-text-to-sql | adapter | — | 6.74B | M | llama2 | maximuslee07 | 0 | 553 |
| monsterapi/codellama_7b_DolphinCoder | adapter | — | — | — | apache-2.0 | monsterapi | 0 | 528 |
| codersan/Enlighten_CodeCompletion | adapter | — | — | — | — | codersan | 7 | 103 |
| alphahg/CodeLlama-7b-hf-rust-finetune | finetune | — | — | — | llama2 | alphahg | 1 | 399 |
| shumi2011/vtb_codeV1_7b | adapter | GGUF | 6.74B | M | — | shumi2011 | 1 | 392 |
| HARRY07979/CodeLlama-7b-hf-Q4_K_M-GGUF | quantized | GGUF | — | — | llama2 | HARRY07979 | 0 | 437 |
| medxiaorudan/CodeLlama_CPP_FineTuned | adapter | — | — | — | llama2 | medxiaorudan | 2 | 311 |
| BohdanPetryshyn/codellama-7b-openapi-completion-ctx-lvl-fim-no-spm-inf-seq-a-32 | adapter | — | — | — | llama2 | BohdanPetryshyn | 6 | 49 |
| liodon-ai/CodeLlama-7b-hf-imatrix-GGUF | quantized | imatrix | — | — | other | liodon-ai | 0 | 340 |
| KonstantinKislov/CodeLlama_adapter_for_solving_the_problem_of_increasing_the_readability_of_decompiled_C_code | adapter | — | — | — | — | KonstantinKislov | 3 | 185 |
| liodon-ai/CodeLlama-7b-hf-ONNX | quantized | — | — | — | other | liodon-ai | 0 | 292 |
| PopularPenguin/CodeLlama-TextToSparql | adapter | — | — | — | llama2 | PopularPenguin | 0 | 290 |
| swordfish7412/Amigo_1.0 | adapter | — | — | — | mit | swordfish7412 | 2 | 174 |
| SillyTilly/CodeLLama-7b-Poison-reup | finetune | — | 6.74B | M | llama2 | SillyTilly | 1 | 222 |
| ABerlanga/code-llama-7b-text-to-sql | adapter | — | — | — | llama2 | ABerlanga | 2 | 165 |
| ken123777/codellama-7b-code-review-v1 | finetune | — | 6.74B | M | mit | ken123777 | 1 | 214 |
| choprahetarth/CodeLLaMa-SLERP | merge | — | 6.74B | M | — | choprahetarth | 0 | 261 |
| dhuynh95/EvilCodeLlama-7b | adapter | — | 2.70B | M | llama2 | dhuynh95 | 1 | 206 |
| HARRY07979/CodeLlama-7b-hf-IQ4_NL-GGUF | quantized | GGUF | — | — | llama2 | HARRY07979 | 0 | 251 |
| noeloco/modeltest1 | adapter | — | — | — | llama2 | noeloco | 0 | 242 |
| gair-prox/CodeLlama-7B-ProXMath | finetune | — | — | — | llama2 | gair-prox | 1 | 185 |
| Date | Commit | SHA |
|---|---|---|
| 2024-04-12 | Update README.md | 6c284d1 |
| 2024-01-29 | Update README.md | 7f22f0a |
| 2023-10-27 | Fix link to responsible use guide (#20) | bc52832 |
| 2023-08-28 | Update README.md | 3773f63 |
| 2023-08-28 | delete unused checkpoints (#12) | a6a8170 |
| 2023-08-28 | Upload LlamaForCausalLM | ab8c802 |
| 2023-08-28 | CodeLlamaTokenizer (#11) | 0b6e5ef |
| 2023-08-25 | Model capabilities (#9) | 533ac5f |
| 2023-08-25 | Install transformers from main (#8) | 82ad5cd |
| 2023-08-25 | use 6 shards instead of 2 | be52f4a |
| 2023-08-25 | Adding `safetensors` variant of this model (#5) | 0d6f9ee |
| 2023-08-25 | Update README.md | 7571482 |
| 2023-08-25 | Fix 13b and 34b instruct links, small typo (#2) | 4a90c02 |
| 2023-08-24 | Upload 2 files | 31eddd0 |
| 2023-08-24 | Update README.md | 304c992 |
| 2023-08-24 | Update README.md | b9a2245 |
| 2023-08-24 | Update README.md | f274875 |
| 2023-08-24 | add model weights | ba606a6 |
| 2023-08-24 | Update README.md | aa112c5 |
| 2023-08-24 | Update README.md | 7202730 |
| 2023-08-24 | Update README.md | b0ef4a0 |
| 2023-08-24 | Update README.md | 8a68eed |
| 2023-08-24 | Update README.md | 485cb6c |
| 2023-08-24 | Update README.md | 7e58ad0 |
| 2023-08-24 | Create README.md | bca487f |
| 2023-08-24 | initial commit | 7d63311 |
Hosted endpoints observed for CodeLlama-7b-hf, 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 | codellama/CodeLlama-7b-hf | — | — | — | — | — | — | — | 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.
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).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:39 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:10 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.
