Mistral Nemo 12B
consumer- 12.2B
- 128k
- apache 2.0
- 🇫🇷 France
- Jul 2024
Scores
Score per dollar
3444 pts per $/M input
general_score (62) divided by cheapest input price ($0.02/M). Higher is better value. See live pricing.
Related models
Save your hardware and every model page answers the real question: will it run on your machine, and how fast?
Join free - save your rig →Run it locally
Per-quant memory needs and a static "can you run it?" reference - no rig entry required
The reference hardware
22 reference configs, drawn in-house. Scroll for more.
Can you run it? - reference rigs
| Rig | Q4_K_M | Q8_0 |
|---|---|---|
| 4x H100 80GB (320GB) | fast 1009.4t/s | fast 558.3t/s |
| NVIDIA DGX Station 748GB | fast 602.6t/s | fast 333.3t/s |
| 8x RTX 3090 rack (192GB) | fast 564.2t/s | fast 312.0t/s |
| 4x RTX 5090 (128GB) | fast 539.9t/s | fast 298.6t/s |
| AMD Instinct MI300X (192GB) | fast 401.1t/s | fast 221.8t/s |
| 4x RTX 4090 (96GB) | fast 303.7t/s | fast 168.0t/s |
| 2x RTX 5090 (64GB) | fast 270.0t/s | fast 149.3t/s |
| 2x RTX 3090 (48GB) | fast 141.0t/s | fast 78.0t/s |
| Single RTX 5090 (32GB) | fast 135.0t/s | fast 74.7t/s |
| RTX PRO 6000 Blackwell (96GB) | fast 135.0t/s | fast 74.7t/s |
| Mac Studio M4 Ultra 192GB | fast 89.7t/s | fast 49.6t/s |
| Mac Studio M4 Ultra 512GB | fast 89.7t/s | fast 49.6t/s |
| Single RTX 4090 (24GB) | fast 75.9t/s | fast 42.0t/s |
| MacBook Pro M5 Max 128GB | fast 50.5t/s | fast 27.9t/s |
| Single GTX 1080 Ti (11GB) | fast 36.5t/s | offload |
| Dual EPYC 9004 + 768GB DDR5-4800 | fast 34.7t/s | ok 19.2t/s |
| DGX Spark 128GB unified | fast 20.6t/s | ok 11.4t/s |
| Ryzen AI Max+ 395 128GB | ok 19.3t/s | ok 10.7t/s |
| Jetson AGX Orin 64GB | ok 15.4t/s | ok 8.5t/s |
| Epyc + 512GB DDR4-3200 + 2x RTX 3090 | ok 15.4t/s | ok 8.5t/s |
| Epyc + 512GB DDR4-2400 + 2x RTX 3090 | ok 11.6t/s | slow 6.4t/s |
| NVIDIA Jetson Orin NX 16GB | slow 7.7t/s | slow 4.3t/s |
Fit tiers use the same will-it-run logic as the rig finder. For comfortable fits, the badge reflects decode speed: fast >=20 t/s, ok 8-20 t/s, slow <8 t/s. t/s is a bandwidth estimate, not a measured benchmark.
Download options
Or run it in the cloud
Live per-provider pricing, throughput and uptime - refreshed about 9 hours ago via OpenRouter. Click a column to sort.
| Provider | Type | Input $/M | Output $/M | Cache $/M | Tok/s | Latency | Uptime | Value |
|---|---|---|---|---|---|---|---|---|
|
Io Net
|
API | 0.04 | 0.13 | 0.024 | - | - | 100.00% | best uptime |
|
DeepInfra
|
API | 0.02 | 0.03 | - | - | - | 99.97% | |
|
Parasail
|
API | 0.03 | 0.03 | - | - | - | 99.94% | |
|
DekaLLM
|
API | 0.02 | 0.03 | - | - | - | 99.80% | cheapest |
|
Mistral
|
API | 0.15 | 0.15 | 0.015 | - | - | 98.67% | |
|
Novita
avoid
|
API | 0.04 | 0.17 | - | - | - | 60.71% |
Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.
Detailed API pricing page + JSON endpoint →
See who runs Mistral AI in production →
Inference cost over time
Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.