Qwen2.5 7B Instruct
Qwenhuggingface.co/Qwen/Qwen2.5-7B-Instruct
Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
Updated 49 min ago · first seen 11 Sept 2026
model_01M294WWNCEDHW7G4RZQW1A9EZ
- Parameters
- 7.62B
- T2 · 52 min ago
- Context
- 32.8K tokens
- T2 · 53 min ago
- Released
- 16 Oct 2024
- T2 · 53 min ago
- Knowledge cutoff
- Jun 2024
- T2 · 53 min ago
Specification
- Release date
- 16 Oct 2024
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 52 min agomedium
- Parameters
- 7.62B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 52 min agomedium
- Context window
- 32.8K tokens
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Max output
- 29.5K tokens
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Knowledge cutoff
- Jun 2024
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Tokenizer
- Qwen
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Hugging Face repo
- Qwen/Qwen2.5-7B-Instruct
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 52 min agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 52 min agomedium
- Downloads
- 10,059,299
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 49 min agomedium
- Likes
- 1,588
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 49 min agomedium
- Instruct type
- chatml
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Last modified
- 2025-01-12T02:10:10+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 52 min agomedium
- Openrouter id
- qwen/qwen-2.5-7b-instruct
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Supported parameters
- frequency_penalty, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
22
Source tiers
T222
Freshest observation
49 min ago
Conflicts
None
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Unavailable
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 32.8K tokens
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Max output
- 29.5K tokens
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Knowledge cutoff
- Jun 2024
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
- Tokenizer
- Qwen
Source:OpenRouter public model & pricing listingT2observed 53 min agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenRouterqwen/qwen-2.5-7b-instruct | $0.10 | $0.20 | — | — | 32.8K | 53 min ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- OpenRouter
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| Apple M3 Ultra | 4bit | — | 4.9 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 4.9 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 4.9 GB | Yes |
| Apple M2 Ultra | 4bit | — | 4.9 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 4.9 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 4.9 GB | Yes |
| Apple M1 Ultra | 4bit | — | 4.9 GB | Yes |
| Apple M3 Max | 4bit | — | 4.9 GB | Yes |
| Apple M4 Max | 4bit | — | 4.9 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 4.9 GB | Yes |
| Apple M2 Max | 4bit | — | 4.9 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 4.9 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 4.9 GB | Yes |
| Apple M1 Max | 4bit | — | 4.9 GB | Yes |
| Apple M4 Pro | 4bit | — | 4.9 GB | Yes |
| Apple M3 Pro | 4bit | — | 4.9 GB | Yes |
| Apple M1 Pro | 4bit | — | 4.9 GB | Yes |
| Apple M2 Pro | 4bit | — | 4.9 GB | Yes |
| Apple M4 | 4bit | — | 4.9 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 4.9 GB | Yes |
| Apple M2 | 4bit | — | 4.9 GB | Yes |
| Apple M3 | 4bit | — | 4.9 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 4.9 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 4.9 GB | Yes |
| Apple M1 | 4bit | — | 4.9 GB | Yes |
Ancestors 0
None recorded.
Descendants 1
- BAGEL-7B-MoT14.7B
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Instruct type
Instruct typeinstruct_type1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| chatml | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
OpenRouter lists Qwen2.5 7B Instruct at $0.1 in / $0.2 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/bartowski/Qwen2.5-7B-Instruct-GGUF | model_page | T2· Quality secondary | 38 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/ByteDance-Seed/BAGEL-7B-MoT | model_page | T2· Quality secondary | 39 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=Qwen&p=0&sort=downloads | listing | T2· Quality secondary | 49 min ago | 2 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 53 min ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.