Updated 16 min ago · first seen 11 Sept 2026
model_01M294WVWTMVFWBHFME6TCE338
- Parameters
- 30.5B
- T2 · 2 h ago
- Context
- 256K tokens
- T2 · 38 min ago
- Released
- 5 Jun 2026
- T2 · 2 h ago
- License
- apache-2.0
- T2 · 2 h ago
Specification
- Release date
- 5 Jun 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- License
- apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Architecture
- Cohere2MoeForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Parameters
- 30.5B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Context window
- 256K tokens
Source:Artificial AnalysisT2observed 38 min agomedium
- File size
- 61.0 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hugging Face repo
- CohereLabs/North-Mini-Code-1.0
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads
- 11,283
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium
- Likes
- 565
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Last modified
- 2026-06-15T04:32:41+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Aa median output tokens per second
- 70.6
Source:Artificial AnalysisT2observed 38 min agomedium
- Downloads all time
- 77,467
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 min agomedium
- Model type
- cohere2_moe
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Openrouter id
- cohere/north-mini-code
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Tags
- transformers, safetensors, cohere2_moe, text-generation, chat, code, agent
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Weights dtype
- BF16
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h 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
16 min ago
Conflicts
None
Modalities
Modalities unavailable.
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Yes
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 256K tokens
Source:Artificial AnalysisT2observed 38 min agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 37.43% | pass^1 | aa_slug=north-mini-code · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Artificial Analysis Intelligence Index | 12.84 | index | aa_slug=north-mini-code · version=4.3 · estimated=true | — | artificialanalysis.aiT2 |
| GPQA | 75.66% | accuracy | aa_slug=north-mini-code · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 11.08% | accuracy | aa_slug=north-mini-code · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 57.55% | accuracy | aa_slug=north-mini-code · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| SciCode | 38.77% | accuracy | aa_slug=north-mini-code · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 31.06% | accuracy | aa_slug=north-mini-code · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 35.58% | accuracy | aa_slug=north-mini-code · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 0.51% | accuracy | aa_slug=north-mini-code · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| Cohere APIcohere/north-mini-code:free | $0 | $0 | — | — | 256K | 43 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
- Cohere API
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 |
|---|---|---|---|---|
| NVIDIA DGX B200 | 4bit | 1,440 GB | 18.0 GB | Yes |
| Apple M3 Ultra | 4bit | — | 18.0 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 18.0 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 18.0 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 18.0 GB | Yes |
| Apple M2 Ultra | 4bit | — | 18.0 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 18.0 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 18.0 GB | Yes |
| NVIDIA H200 NVL | 4bit | 141 GB | 18.0 GB | Yes |
| Apple M1 Ultra | 4bit | — | 18.0 GB | Yes |
| Apple M3 Max | 4bit | — | 18.0 GB | Yes |
| Apple M4 Max | 4bit | — | 18.0 GB | Yes |
| Mac Studio (Apple M5 Max) | 4bit | — | 18.0 GB | Yes |
| MacBook Pro (Apple M5 Max) | 4bit | — | 18.0 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 18.0 GB | Yes |
| Apple M2 Max | 4bit | — | 18.0 GB | Yes |
| NVIDIA H100 NVL | 4bit | 94 GB | 18.0 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 18.0 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 18.0 GB | Yes |
| Apple M1 Max | 4bit | — | 18.0 GB | Yes |
| Apple M4 Pro | 4bit | — | 18.0 GB | Yes |
| Mac mini (Apple M5 Pro) | 4bit | — | 18.0 GB | Yes |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 18.0 GB | Yes |
| Apple M3 Pro | 4bit | — | 18.0 GB | Yes |
| Apple M1 Pro | 4bit | — | 18.0 GB | Yes |
| Apple M2 Pro | 4bit | — | 18.0 GB | Yes |
| Apple M4 | 4bit | — | 18.0 GB | Yes |
| iMac (Apple M4) | 4bit | — | 18.0 GB | Yes |
| Mac mini (Apple M6) | 4bit | — | 18.0 GB | Yes |
| MacBook Air (Apple M5) | 4bit | — | 18.0 GB | Yes |
| MacBook Pro (Apple M5) | 4bit | — | 18.0 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 18.0 GB | Yes |
| Apple M2 | 4bit | — | 18.0 GB | Yes |
| Apple M3 | 4bit | — | 18.0 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 18.0 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 18.0 GB | Yes |
| Apple M1 | 4bit | — | 18.0 GB | No |
No lineage recorded
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 · File size
File sizefile_size_gb1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 61.0 GB | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | 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 →
North Mini Code (free) scores 31.06% on Terminal-Bench
artificial_analysisNorth Mini Code (free) scores 35.58% on Terminal-Bench
artificial_analysisNorth Mini Code (free) scores 0.51% on Terminal-Bench
artificial_analysisNorth Mini Code (free) scores 37.43% on τ²-bench
artificial_analysisNorth Mini Code (free) scores 57.55% on IFBench
artificial_analysisNorth Mini Code (free) scores 38.77% on SciCode
artificial_analysisNorth Mini Code (free) scores 11.08% on Humanity's Last Exam
artificial_analysisNorth Mini Code (free) scores 75.66% on GPQA
artificial_analysisNorth Mini Code (free) scores 12.84 on Artificial Analysis Intelligence Index
artificial_analysisCohere API lists North Mini Code (free) at $0 in / $0 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/CohereLabs/North-Mini-Code-1.0 | model_page | T2· Quality secondary | 16 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=CohereLabs&p=0&sort=downloads | listing | T2· Quality secondary | 29 min ago | 3 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 38 min ago | 1 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 43 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/CohereLabs/North-Mini-Code-1.0/raw/main/README.md | model_card | T2· Quality secondary | 1 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.