Up to date
Qwen tongyi-qianwen out 3 years ago
7.25B parameters, text in, text out.
Verified 2026-10-25 Rank #705 in LLMs · score 72 method v1 Sources 3 Downloads 30d 4.6k · #550 of 619 tracked
Picked by rule from 1 tracked piece: the lab's own post, the most shared, a field report, the latest.
The Qwen Team released CodeQwen1.5-7B, an open-source code model pretrained on 3 trillion tokens.
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.
No API provider serves it, so its downloads are people running it themselves: 22 quantized builds.
Weights only, an estimate: leave room for the KV cache. Method
About 4.4 GB at INT4, 8.7 GB at FP8, 17 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 (2024-04-15), amber triangles are 1 dated article (each links to it).
45 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 | Qwen2ForCausalLM |
| Model type | qwen2 |
| Params by dtype | BF16: 7,250,284,544 |
| Size band | M |
| MoE | no |
| Papers | arXiv:2309.16609 |
| License | tongyi-qianwen (other) |
| Hub snapshot | 2026-10-25 |
Weights-only memory for CodeQwen1.5-7B-Chat: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 17 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 8.7 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 4.4 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 22finetune: 8merge: 3adapter: 12
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| QuantFactory/CodeQwen1.5-7B-Chat-GGUF | quantized | GGUF | — | — | other | QuantFactory | 1 | 12.8k |
| second-state/CodeQwen1.5-7B-Chat-GGUF | quantized | GGUF | — | — | other | second-state | 3 | 11.9k |
| mradermacher/CodeQwen1.5-7B-Chat-i1-GGUF | quantized | GGUF | — | — | other | mradermacher | 1 | 8k |
| CISCai/CodeQwen1.5-7B-Chat-SOTA-GGUF | quantized | GGUF | — | — | other | CISCai | 1 | 7.2k |
| mradermacher/CodeQwen1.5-7B-Chat-GGUF | quantized | GGUF | — | — | other | mradermacher | 1 | 3.9k |
| DevQuasar-9/Qwen.CodeQwen1.5-7B-Chat-GGUF | quantized | GGUF | — | — | — | DevQuasar-9 | 0 | 2k |
| Zhaorun/CodeQwen1.5-7B-trojan-clas2024-test | finetune | — | 7.25B | M | apache-2.0 | Zhaorun | 0 | 1.7k |
| AbteeXAILab/lumynax-coder-codeqwen15-7b-chat-gguf | quantized | gguf | — | — | apache-2.0 | AbteeXAILab | 0 | 921 |
| Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw | quantized | exl2 | — | — | other | Dracones | 4 | 91 |
| Wwayu/CodeQwen1.5-7B-Chat-mlx-6Bit | quantized | mlx | 7.25B | M | other | Wwayu | 0 | 270 |
| dohrisalim/Code-7B-slerp | merge | — | 7.25B | M | — | dohrisalim | 1 | 209 |
| hellork/CodeQwen1.5-7B-Chat-IQ4_NL-GGUF | quantized | GGUF | — | — | other | hellork | 0 | 244 |
| ByteBrew23/SuperCode | finetune | — | 7.25B | M | — | ByteBrew23 | 0 | 223 |
| Jebadiah/Aria-CodeQwen-stone | merge | — | 7.24B | M | — | Jebadiah | 0 | 216 |
| Dracones/CodeQwen1.5-7B-Chat_exl2_4.0bpw | quantized | exl2 | — | — | other | Dracones | 0 | 195 |
| Aashraf995/EVOCoder-7B | merge | — | 7.25B | M | — | Aashraf995 | 2 | 92 |
| Dracones/CodeQwen1.5-7B-Chat_exl2_7.0bpw | quantized | exl2 | — | — | other | Dracones | 0 | 189 |
| Dracones/CodeQwen1.5-7B-Chat_exl2_3.5bpw | quantized | exl2 | — | — | other | Dracones | 0 | 188 |
| vahhab70/CodeQwen1.5-7B-Chat-Q4_K_M-GGUF | quantized | GGUF | — | — | other | vahhab70 | 0 | 121 |
| Aashraf995/CodeQwen1.5-7B-Chat-Q4_K_M-GGUF | quantized | GGUF | — | — | other | Aashraf995 | 0 | 120 |
| LLM-EDA/VeriPrefer-CodeQwen1.5-7B | finetune | — | 7.25B | M | apache-2.0 | LLM-EDA | 0 | 109 |
| reach-vb/CodeQwen1.5-7B-Chat-Q3_K_S-GGUF | quantized | GGUF | — | — | other | reach-vb | 1 | 58 |
| mrG46487/CodeQwen1.5-7B-Chat-Q4_K_M-GGUF | quantized | GGUF | — | — | other | mrG46487 | 0 | 94 |
| Dracones/CodeQwen1.5-7B-Chat_exl2_6.0bpw | quantized | exl2 | — | — | other | Dracones | 0 | 81 |
| Dracones/CodeQwen1.5-7B-Chat_exl2_2.5bpw | quantized | exl2 | — | — | other | Dracones | 0 | 80 |
| Dracones/CodeQwen1.5-7B-Chat_exl2_5.0bpw | quantized | exl2 | — | — | other | Dracones | 0 | 72 |
| SepKeyHF/PyomoCodeQwen1.5-7B-Chat | adapter | — | — | — | — | SepKeyHF | 0 | 71 |
| Dracones/CodeQwen1.5-7B-Chat_exl2_2.75bpw | quantized | exl2 | — | — | other | Dracones | 0 | 61 |
| Dracones/CodeQwen1.5-7B-Chat_exl2_3.0bpw | quantized | exl2 | — | — | other | Dracones | 0 | 59 |
| nguyenthanhdo/ViMath-CodeQwen1.5-7B-LORA | adapter | — | — | — | other | nguyenthanhdo | 0 | 55 |
| nicon899/codeqwen-7b-recipe-app_20240819_162703 | finetune | — | 7.25B | M | other | nicon899 | 0 | 52 |
| nicon899/codeqwen-7b-recipe-app_20240819_175513 | finetune | — | 7.25B | M | other | nicon899 | 0 | 46 |
| bejorock/autotrain-5jagy-lmsq4 | finetune | — | — | — | other | bejorock | 0 | 46 |
| vdavidr/CodeQwen1.5-7B-Chat_Finetuned_dataset_size_52_epochs_10_2024-06-08_19-19-20 | adapter | — | — | — | other | vdavidr | 0 | 40 |
| vdavidr/CodeQwen1.5-7B-Chat_components_FI_dataset_size_52_epochs_10_2024-06-13_03-26-06_22016831 | adapter | — | 7.25B | M | other | vdavidr | 0 | 40 |
| nicon899/codeqwen-7b-recipe-app | adapter | — | 7.25B | M | other | nicon899 | 0 | 37 |
| nicon899/code-llama-7b-recipe-app | adapter | — | — | — | other | nicon899 | 0 | 35 |
| nguyenthanhdo/ViMath-PAL-CodeQwen1.5-7B-LORA | adapter | — | — | — | other | nguyenthanhdo | 0 | 33 |
| vdavidr/CodeQwen1.5-7B-Chat_components_dataset_size_52_epochs_10_2024-06-13_03-26-06_22016823 | adapter | — | 7.25B | M | other | vdavidr | 0 | 32 |
| nicon899/codeqwen-7b-recipe-app_20240815180858 | adapter | — | — | — | other | nicon899 | 0 | 31 |
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 · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-09 02:04 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.
