- Size
- 7.6B parameterscounted from the safetensors header on the Hub
- Licence
- custom, read it, Apache License 2.0Our reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
- On the Hub since
- 15 Sep 2024the date the repo was created
- Context length
- 128k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Qwen2ForCausalLM
- On Hugging Face
- Qwen/Qwen2.5-7B514k downloads in the last 30 days, 344 likes
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.44 GB, worked out from the model's config (Qwen/Qwen2.5-7B), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
Mungert/Qwen2.5-7B-Instruct-1M-GGUF (converted by Mungert), 3.9k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 3.0 GBfile size | 4.0 GB3.0 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ3_XXSOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ3_XXSDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-iq3_xxs.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| IQ3_XS | 3.2 GBfile size | 4.1 GB3.2 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ3_XSOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ3_XSDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-iq3_xs.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q3_K_S | 3.3 GBfile size | 4.3 GB3.3 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q3_K_SOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q3_K_SDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-q3_k_s.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| IQ3_S | 3.3 GBfile size | 4.3 GB3.3 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ3_SOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ3_SDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-iq3_s.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| IQ3_M | 3.4 GBfile size | 4.3 GB3.4 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ3_MOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ3_MDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-iq3_m.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q3_K_M | 3.6 GBfile size | 4.5 GB3.6 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q3_K_MOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q3_K_MDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-q3_k_m.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| IQ4_XS | 3.9 GBfile size | 4.9 GB3.9 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ4_XSOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ4_XSDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-iq4_xs.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q4_0 | 4.0 GBfile size | 4.9 GB4.0 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0Ollama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0Download hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-q4_0.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| IQ4_NL | 4.1 GBfile size | 5.1 GB4.1 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ4_NLOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:IQ4_NLDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-iq4_nl.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q4_K_S | 4.3 GBfile size | 5.2 GB4.3 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_SOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_SDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-q4_k_s.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q4_1 | 4.4 GBfile size | 5.4 GB4.4 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q4_1Ollama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q4_1Download hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-q4_1.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q4_K_M | 4.5 GBfile size | 5.4 GB4.5 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_MOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q4_K_MDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-q4_k_m.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q5_0 | 4.9 GBfile size | 5.8 GB4.9 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q5_0Ollama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q5_0Download hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-q5_0.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q5_K_S | 5.0 GBfile size | 6.0 GB5.0 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q5_K_SOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q5_K_SDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-q5_k_s.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q5_K_M | 5.1 GBfile size | 6.1 GB5.1 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q5_K_MOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q5_K_MDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-q5_k_m.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q5_1 | 5.3 GBfile size | 6.3 GB5.3 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q5_1Ollama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q5_1Download hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-q5_1.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q4_K | 5.7 GBfile size | 6.6 GB5.7 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q4_KOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q4_KDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-bf16-q4_k.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q6_K_M | 5.8 GBfile size | 6.8 GB5.8 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q6_K_MOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q6_K_MDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-q6_k_m.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q6_K | 7.0 GBfile size | 8.0 GB7.0 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q6_KOllama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q6_KDownload hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-bf16-q6_k.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| Q8_0 | 8.5 GBfile size | 9.4 GB8.5 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q8_0Ollama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:Q8_0Download hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-bf16-q8_0.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
| BF16 | 14.2 GBfile size | 15.1 GB14.2 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf Mungert/Qwen2.5-7B-Instruct-1M-GGUF:BF16Ollama ollama run hf.co/Mungert/Qwen2.5-7B-Instruct-1M-GGUF:BF16Download hf download Mungert/Qwen2.5-7B-Instruct-1M-GGUF --include "Qwen2.5-7B-Instruct-1M-bf16.gguf" --local-dir Qwen2.5-7B-Instruct-1M-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 14.2 GBfile size | 15.1 GB14.2 + 0.44 + 0.50 |
hf download Qwen/Qwen2.5-7B --local-dir Qwen2.5-7BOther conversions (16; sizes not read)
- unsloth/Qwen2.5-7B-unsloth-bnb-4bit bitsandbytes, 4bit, 5.7k downloads
- unsloth/Qwen2.5-7B-bnb-4bit bitsandbytes, 4bit, 3.9k downloads
- RedHatAI/Qwen2.5-7B-quantized.w8a16 Other, 115 downloads
- Xylolabs/Qwen2.5-7B-Tenstorrent-Tensix-BFP4-MLP Other, 92 downloads
- RedHatAI/Qwen2.5-7B-quantized.w8a8 Other, w8a8, 86 downloads
- Xylolabs/Qwen2.5-7B-Tenstorrent-Tensix-BFP8 Other, 81 downloads
- RedHatAI/Qwen2.5-7B-FP8-dynamic FP8, 74 downloads
- CalamitousFelicitousness/Qwen2.5-7B-Instruct-fp8-dynamic FP8, 64 downloads
- LoneStriker/Qwen2.5-7B-Instruct-4.0bpw-h6-exl2 EXL2, 23 downloads
- Phuc2005/Qwen2.5-7B-AWQ-W4A16-g128 AWQ, w4a16, 17 downloads
- genovalabs/Qwen2.5-7B-Instruct-fp8-dynamic FP8, 15 downloads
- iproskurina/Qwen2.5-7B-Instruct-gptqmodel-4bit-g32 GPTQ, 4bit, 13 downloads
- LoneStriker/Qwen2.5-7B-Instruct-6.0bpw-h6-exl2 EXL2, 10 downloads
- LoneStriker/Qwen2.5-7B-Instruct-5.0bpw-h6-exl2 EXL2, 9 downloads
- async0x42/Qwen2.5-7B-Instruct-1M-exl2_4.65bpw EXL2, 9 downloads
- osllmai-community/Qwen2.5-7B-bnb-4bit bitsandbytes, 4bit, 4 downloads
The Hub tags 90 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- Qwen/Qwen2.5-7B-Instruct7.6B6.4MReviewed
- Qwen/Qwen2.5-Coder-7B7.6B366kReviewed
- Qwen/Qwen2.5-7B-Instruct-1M7.6B34kUnreviewed
- Qwen/Qwen2.5-Math-7B7.6B25kUnreviewed
- mlx-community/Qwen2.5-7B-Instruct-4bit13kUnreviewed
- MiniMaxAI/SynLogic-7B7.6B2.3kUnreviewed
- internlm/OREAL-7B-SFT7.6B2.1kUnreviewed
- internlm/SWE-Fixer-Retriever-7B7.6B1.9kUnreviewed
- nvidia/OpenReasoning-Nemotron-7B7.6B1.1kUnreviewed
- tencent/WeDLM-7B-Base7.6B218Unreviewed
- ByteDance-Seed/AHN-DN-for-Qwen-2.5-Instruct-7B204Unreviewed
- ByteDance-Seed/AHN-Mamba2-for-Qwen-2.5-Instruct-7B190Unreviewed
- ByteDance-Seed/AHN-GDN-for-Qwen-2.5-Instruct-7B179Unreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.