Up to date
mistralai Apache 2.0 out 3 years ago
7.24B parameters, text in, text out, 32K tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #91 in LLMs · score 100.7 method v1 Sources 3 Downloads 30d 117.2k · #301 of 619 tracked
Changed this week: 2 new quantized builds on the Hub (31 in all).2026-10-24
Picked by rule from 9 tracked pieces: the lab's own post, the most shared, a field report, the latest.
Mistral AI released the mistral-7b-instruct-v0.1, a 7B instruction-tuned LLM licensed under Apache 2.0 with an 8,000 token context length.
The 3 picks above, plus these 6. 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; 31 quantized builds for local use; a big base for builders (818 fine-tunes, adapters and merges).
Top Spaces running it: allenai/WildBench ♥ 232 · osanseviero/mistral-super-fast ♥ 213 · allenai/ZebraLogic ♥ 95 · chansung/vid2persona ♥ 88
Weights only, an estimate: leave room for the KV cache. Method
About 4.3 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 (2023-09-27), amber triangles are 4 dated articles (each links to it), grey ticks are repo commits.
849 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 | MistralForCausalLM |
| Model type | mistral |
| Dtype | bfloat16 |
| Params by dtype | BF16: 7,241,732,096 |
| Size band | M |
| MoE | no |
| Context length | 32,768 (config.json max_position_embeddings) |
| Papers | arXiv:2310.06825 |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · MistralForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · MistralForCausalLM · 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 Mistral-7B-Instruct-v0.1: 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) | 4.3 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
Base model: mistralai/Mistral-7B-v0.1
quantized: 31merge: 44finetune: 332adapter: 442
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| TheBloke/Mistral-7B-Instruct-v0.1-GPTQ | quantized | GPTQ | 7.24B | M | apache-2.0 | TheBloke | 85 | 4M |
| TheBloke/Mistral-7B-Instruct-v0.1-GGUF | quantized | GGUF | — | — | apache-2.0 | TheBloke | 615 | 2.9M |
| TheBloke/Mistral-7B-Instruct-v0.1-AWQ | quantized | AWQ | 7.24B | M | apache-2.0 | TheBloke | 38 | 1.1M |
| BioMistral/BioMistral-7B-DARE | merge | — | 7.24B | M | apache-2.0 | BioMistral | 24 | 95.1k |
| Commencis/Commencis-LLM | finetune | — | 7.24B | M | apache-2.0 | Commencis | 16 | 50.8k |
| mradermacher/Mistral-7B-Instruct-v0.1-i1-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 1 | 19.4k |
| second-state/Mistral-7B-Instruct-v0.1-GGUF | quantized | GGUF | — | — | apache-2.0 | second-state | 2 | 18.1k |
| BioMistral/BioMistral-7B-SLERP | merge | — | 7.24B | M | apache-2.0 | BioMistral | 8 | 17k |
| itlwas/Mistral-7B-Instruct-v0.1-Q4_K_M-GGUF | quantized | GGUF | — | — | apache-2.0 | itlwas | 6 | 15.7k |
| BioMistral/BioMistral-7B-TIES | merge | — | 7.24B | M | apache-2.0 | BioMistral | 2 | 15k |
| ik-ram28/MedMistralInstruct-CPT-7B | finetune | — | 7.24B | M | apache-2.0 | ik-ram28 | 1 | 12.9k |
| BioMistral/BioMistral-7B-DARE-GGUF | merge | GGUF | — | — | apache-2.0 | BioMistral | 14 | 11.8k |
| osanseviero/mistral-instruct-frankenmerge | merge | — | 8.99B | M | apache-2.0 | osanseviero | 2 | 12.3k |
| osanseviero/mistral-instruct-moe-experimental | merge | — | 12.9B | L | apache-2.0 | osanseviero | 2 | 12.3k |
| osanseviero/mistral-instruct-slerp | merge | — | 7.24B | M | apache-2.0 | osanseviero | 1 | 12.1k |
| Corianas/NearalMistral-2x7B | merge | — | 12.9B | L | apache-2.0 | Corianas | 1 | 10k |
| QuantFactory/Mistral-7B-Instruct-v0.1-GGUF | quantized | GGUF | — | — | apache-2.0 | QuantFactory | 1 | 9.9k |
| MaziyarPanahi/Mistral-7B-Instruct-v0.1-GGUF | quantized | GGUF | — | — | apache-2.0 | MaziyarPanahi | 1 | 9k |
| mradermacher/Mistral-7B-Instruct-v0.1-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 1 | 5.7k |
| jpquiroga/Mistral_7B_ties_merge_instruct_open_orca | merge | — | 7.24B | M | apache-2.0 | jpquiroga | 0 | 5.3k |
| OpenVINO/mistral-7b-instruct-v0.1-int4-ov | quantized | int4 | — | — | apache-2.0 | OpenVINO | 1 | 3.7k |
| DevQuasar-8/mistralai.Mistral-7B-Instruct-v0.1-GGUF | quantized | GGUF | — | — | — | DevQuasar-8 | 0 | 3.6k |
| GeoGPT-Research-Project/GeoEmbedding | finetune | — | 7.11B | M | apache-2.0 | GeoGPT-Research-Project | 15 | 2.1k |
| Kquant03/BioMistral-7B-TIES-GGUF | merge | GGUF | — | — | apache-2.0 | Kquant03 | 0 | 2.3k |
| frankmorales2020/Mistral-7B-v0.1_Emotion | adapter | — | — | — | apache-2.0 | frankmorales2020 | 1 | 2k |
| sshh12/Mistral-7B-LoRA-VisionCLIP-LLAVA | finetune | — | — | — | apache-2.0 | sshh12 | 10 | 1k |
| LeroyDyer/Mixtral_Chat_7b | quantized | GGUF | — | — | mit | LeroyDyer | 2 | 1.4k |
| sshh12/Mistral-7B-LoRA-ImageBind-LLAVA | finetune | — | — | — | apache-2.0 | sshh12 | 12 | 851 |
| LoneStriker/BioMistral-7B-SLERP-GGUF | merge | GGUF | — | — | apache-2.0 | LoneStriker | 0 | 1.4k |
| LoneStriker/BioMistral-7B-DARE-GGUF | merge | GGUF | — | — | apache-2.0 | LoneStriker | 0 | 1.4k |
| abhishek-ch/biomistral-7b-synthetic-ehr | merge | — | 7.24B | M | apache-2.0 | abhishek-ch | 4 | 1.1k |
| LilithAdam5/Mistral-7B-Instruct-v0.1-GGUF | quantized | GGUF | — | — | apache-2.0 | LilithAdam5 | 0 | 1.2k |
| leliuga/mistral-7b-instruct-v0.1-bnb-4bit | quantized | -bnb | 7.46B | M | apache-2.0 | leliuga | 0 | 1.2k |
| DhruvalLabs/Mistral-7B-Instruct-v0.1-GGUF | quantized | GGUF | — | — | apache-2.0 | DhruvalLabs | 1 | 1.1k |
| LoneStriker/BioMistral-7B-TIES-GGUF | merge | GGUF | — | — | apache-2.0 | LoneStriker | 0 | 1.2k |
| frankmorales2020/Mistral-7B-v0.1_AviationQA | adapter | — | — | — | apache-2.0 | frankmorales2020 | 1 | 1k |
| MaziyarPanahi/Tess-XS-v1-3-yarn-128K-Mistral-7B-Instruct-v0.1 | merge | — | 7.24B | M | apache-2.0 | MaziyarPanahi | 1 | 1k |
| MaziyarPanahi/Mistral-7B-Instruct-v0.1-GPTQ | finetune | GPTQ | 1.20B | S | apache-2.0 | MaziyarPanahi | 1 | 1k |
| VijayRam1812/Mistral-7B-Business | adapter | — | — | — | apache-2.0 | VijayRam1812 | 1 | 844 |
| MaziyarPanahi/Mistral-7B-Instruct-v0.1-AWQ | quantized | AWQ | 7.24B | M | — | MaziyarPanahi | 1 | 818 |
| Date | Commit | SHA |
|---|---|---|
| 2025-07-24 | Update README.md | ec5deb6 |
| 2025-07-24 | Update README.md | 9db24f5 |
| 2025-07-24 | Update README.md | 4806193 |
| 2025-07-23 | Update README.md | 0f4876c |
| 2024-08-22 | Create tokenizer.model.v1 | 2dcff66 |
| 2024-08-19 | Add base_model metadata (#124) | b54ee4f |
| 2024-08-05 | Update README.md | 1b62ab7 |
| 2024-07-24 | Update README.md | b97858e |
| 2024-07-03 | Align tokenizer with mistral-common (#120) | b54db93 |
| 2024-06-24 | [AUTO] CVST Tokenizer Badger (#119) | 86370fc |
| 2024-06-20 | Updating chat template, trying to make it match with `mistral_common` (#116) | 75c1402 |
| 2024-02-29 | Enable inference & update examples in README to be compatible with soon-to-come ChatWidget (#100) | 73068f3 |
| 2023-12-15 | Update README.md | 9ab9e76 |
| 2023-12-14 | Update config.json (#93) | 464c09a |
| 2023-12-14 | Update config.json | ee84732 |
| 2023-12-12 | Widget with chat format (#90) | 2433b68 |
| 2023-12-11 | Adding `safetensors` variant of this model (#85) | 2364fc7 |
| 2023-12-08 | Update tokenizer_config.json | d2953fb |
| 2023-10-11 | added arxiv | 7ad5799 |
| 2023-10-09 | Restore chat template (#45) | 7961f5a |
| 2023-10-09 | Update tokenizer (#43) | 4464348 |
| 2023-10-06 | Fix INST end token (#37) | 54766df |
| 2023-10-03 | Update inference temperature | 3dc28cf |
| 2023-09-28 | Update README.md | d635d39 |
| 2023-09-28 | Update README.md | 894cc16 |
| 2023-09-28 | Add chat template (#1) | 6d7932e |
| 2023-09-28 | Update README.md (#14) | 8858a59 |
| 2023-09-27 | Update README.md | 2b96272 |
| 2023-09-27 | Update README.md | 3ff897a |
| 2023-09-27 | Update readme | c132c5a |
Hosted endpoints observed for Mistral-7B-Instruct-v0.1, 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 | mistralai/Mistral-7B-Instruct-v0.1 | — | — | — | — | — | — | — | 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 21:33 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:00 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.
