DeepSeek V3 0324
DeepSeek · released Mar 24, 2025 · deepseek-ai/DeepSeek-V3-0324
- Type
- Open weightsMIT License
- Params
- 685B
- Context
- 164K
37B active per word · about 123K words of context
Our take
Written Aug 3, 2026DeepSeek V3 0324 is a large downloadable text model released in March 2025 with a permissive MIT licence. Its coding score on the independent chat leaderboard is its strongest suit, while its maths and instruction-following scores trail within the same profile.
Pick this for coding tasks where its leaderboard score peaks, or for research and commercial derivative work that needs a permissive licence. Use it if you want a mixture-of-experts architecture with a large parameter reservoir at mid-tier API prices. Skip it if you need image, video or audio input, or if you want the fastest throughput and are unwilling to pay the premium host.
The case for it
- Permissive MIT licence allows commercial use, modification and redistribution.
- Coding performance leads its own skill profile, with a 59-point gap over its maths score on the same leaderboard.
- Lowest API price is roughly half the highest offer for input, and about two-thirds for output.
- Highest measured throughput is 88% faster than the slowest tracked host.
The case against it
- Maths and instruction following lag within its own profile, both at least 30 points below its coding peak.
- Text-only: no image, video or audio input or output.
- Throughput is unverified on three of the seven listed providers.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)78th of 143 · 1395.5
CodingWriting and fixing code on its own
Arena Coding88th of 143 · 1428.7
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored DeepSeek V3 0324 for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where DeepSeek V3 0324 placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Radeon RX 7900 XT · 20 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 7 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.27 in / $1.12 out
- Context served
- 164K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| DeepInfrafp4 | $0.24 / $0.90 | 164K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp4 | $0.24 / $0.90 | 164K | 40 tok/s | No | No | Confirmed |
| SiliconFlowfp8 | $0.25 / $1.00 | 164K | 17 tok/s | No | No | Confirmed |
| Novita AI | $0.27 / $1.12 | 164K | not measured | Unknown | Unknown | Unknown |
| OpenRouter | $0.27 / $1.12 | 164K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp8 | $0.27 / $1.12 | 164K | 30 tok/s | No | No | Confirmed |
| Crusoebf16 | $0.50 / $1.50 | 164K | 33 tok/s | No | No | Confirmed |
DeepInfra
OpenRouterAcross the 7 listings we hold: 4 say they do not train on prompts, 0 say they do and 3 do not say. 4 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| DeepInfrafp4 | |||
| DeepInfrafp4 | ✓ | ✓ | ✓ |
| SiliconFlowfp8 | ✓ | ✓ | ✓ |
| Novita AI | |||
| OpenRouter | ✓ | ✓ | ✓ |
| Novita AIfp8 | ✓ | ✗ | ✗ |
| Crusoebf16 | ✗ | ✓ | ✓ |
Tool calling: 4 of 7 listings say yes, 1 says no, 2 publish no parameter list. JSON output: 4 of 7 listings say yes, 1 says no, 2 publish no parameter list. Strict schema: 4 of 7 listings say yes, 1 says no, 2 publish no parameter list.
Models people weigh against DeepSeek V3 0324
When we formed this view
Dates behind this page
Prices last checked 5h ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- 2 of 7 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 3 of 7 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsMIT License, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
MIT License
Fully permissive: do anything with attribution. No patent grant, unlike Apache-2.0.
Identifiers
- Hugging Face
- deepseek-ai/DeepSeek-V3-0324
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- deepseek-deepseek-v3-0324