Mistral Nemo

Tool callingStructured output

Hugging Face Launch post Website Docs

Efficient Mistral-NVIDIA open model for multilingual chat and local deployment

Context: 131K
Released: 2y ago
Parameters: 12B
Input / 1M tokens: $0.03
Output / 1M tokens: $0.03

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Mistral AI
Model family: —
Type: Language model
Predecessor: —
Successor: —
Released: July 1, 2024
Model ID: mistralai/mistral-nemo
Openness: Open weights
License: —
Parameters: 12B
Input modalities: text
Output modalities: text
Modality: text->text
Native context: 1M
Tokenizer: Mistral
Max output tokens: 16K
Knowledge cutoff: 2024-07
Hugging Face: mistralai/Mistral-Nemo-Instruct-2407
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Open-weight builds

Ollama variants

Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.

15 builds

Variant	Parameters	Type	Quantization	Size	Context	Input
mistral-nemo:12b-instruct-2407-fp16	12B	instruct	FP16	25 GB	1M	text
mistral-nemo:12b-instruct-2407-q2_K	12B	instruct	Q2_K	4.8 GB	1M	text
mistral-nemo:12b-instruct-2407-q3_K_L	12B	instruct	Q3_K_L	6.6 GB	1M	text
mistral-nemo:12b-instruct-2407-q3_K_M	12B	instruct	Q3_K_M	6.1 GB	1M	text
mistral-nemo:12b-instruct-2407-q3_K_S	12B	instruct	Q3_K_S	5.5 GB	1M	text
mistral-nemo:latest	12B	instruct	Q4_0	7.1 GB	1M	text
mistral-nemo:12b-instruct-2407-q4_1	12B	instruct	Q4_1	7.8 GB	1M	text
mistral-nemo:12b-instruct-2407-q4_K_M	12B	instruct	Q4_K_M	7.5 GB	1M	text
mistral-nemo:12b-instruct-2407-q4_K_S	12B	instruct	Q4_K_S	7.1 GB	1M	text
mistral-nemo:12b-instruct-2407-q5_0	12B	instruct	Q5_0	8.5 GB	1M	text
mistral-nemo:12b-instruct-2407-q5_1	12B	instruct	Q5_1	9.2 GB	1M	text
mistral-nemo:12b-instruct-2407-q5_K_M	12B	instruct	Q5_K_M	8.7 GB	1M	text
mistral-nemo:12b-instruct-2407-q5_K_S	12B	instruct	Q5_K_S	8.5 GB	1M	text
mistral-nemo:12b-instruct-2407-q6_K	12B	instruct	Q6_K	10 GB	1M	text
mistral-nemo:12b-instruct-2407-q8_0	12B	instruct	Q8_0	13 GB	1M	text

Additional source evidence

Source model: mistral/mistral-nemo
Source family: mistral-nemo
Last updated: 2024-07-01
Knowledge cutoff: 2024-07
Model context: 128K
Model output limit: 128K
Open weights: Yes
File attachments: No
Reasoning: No
Tool calling: Yes
Temperature control: Yes

Downloadable weights

Hugging Face

Complete source record (JSON)

{
  "id": "mistral/mistral-nemo",
  "name": "Mistral Nemo",
  "description": "Efficient Mistral-NVIDIA open model for multilingual chat and local deployment",
  "family": "mistral-nemo",
  "last_updated": "2024-07-01",
  "knowledge": "2024-07",
  "attachment": false,
  "reasoning": false,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 128000,
    "output": 128000
  },
  "release_date": "2024-07-01",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407"
    }
  ]
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Io Net	io-net/fp16	128K	$0.02	$0.02	$0.01	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
DekaLLM	dekallm/fp8	131K	$0.02	$0.03	—	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
DeepInfra	deepinfra/fp8	131K	$0.03	$0.03	—	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Parasail	parasail/fp8	131K	$0.03	$0.03	—	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Mistral	mistral/eu	131K	$0.15	$0.15	$0.02	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware