DeepSeek V4 Flash 0731 vs Inkling 2 Small
Inkling 2 Small leads llmrun Score 134.7 to 127.6; neither fits 24 GB.
Run Inkling 2 Small in the cloud →
Model A · DeepSeek
DeepSeek V4 Flash 0731304.2B · 27.4B active · 1M context · MIT · Jul 2026
Model B · Thinking Machines
Inkling 2 Small594B · 17B active · 1M context · Apache 2.0 · Nov 2026
Choose DeepSeek V4 Flash 0731 if you want…
Lighter on memory
182.8 vs 357.0 GB at Q4_K_M
Choose Inkling 2 Small if you want…
Higher llmrun Score
134.7 vs 127.6
Stronger at reasoning
136.1 vs 128.7
Ahead on the benchmarks
3 of 3 shared boards
Also does vision
DeepSeek V4 Flash 0731 doesn't list it
Newer release
Nov 2026 vs Jul 2026
On your hardware
Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.
8 GB
RTX 4060 · 8 GB tier
DeepSeek V4 Flash 0731
Doesn't fit
smallest quant needs 84.1 GB
Inkling 2 Small
Doesn't fit
smallest quant needs 166.1 GB
12 GB
RTX 3060 12GB · 12 GB tier
DeepSeek V4 Flash 0731
Doesn't fit
smallest quant needs 84.1 GB
Inkling 2 Small
Doesn't fit
smallest quant needs 166.1 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
DeepSeek V4 Flash 0731
Doesn't fit
smallest quant needs 84.1 GB
Inkling 2 Small
Doesn't fit
smallest quant needs 166.1 GB
24 GBreference
RTX 4090 · 24 GB tier
DeepSeek V4 Flash 0731
Doesn't fit
smallest quant needs 84.1 GB
Inkling 2 Small
Doesn't fit
smallest quant needs 166.1 GB
32 GB
RTX 5090 · 32 GB tier
DeepSeek V4 Flash 0731
Doesn't fit
smallest quant needs 84.1 GB
Inkling 2 Small
Doesn't fit
smallest quant needs 166.1 GB
48 GB
RTX A6000 · 48 GB tier
DeepSeek V4 Flash 0731
Doesn't fit
smallest quant needs 84.1 GB
Inkling 2 Small
Doesn't fit
smallest quant needs 166.1 GB
Mac 32 GB
Mac Mini M4 · Macs
DeepSeek V4 Flash 0731
Doesn't fit
smallest quant needs 84.1 GB
Inkling 2 Small
Doesn't fit
smallest quant needs 166.1 GB
Mac 64 GB
Mac Studio M4 Max · Macs
DeepSeek V4 Flash 0731
Doesn't fit
smallest quant needs 84.1 GB
Inkling 2 Small
Doesn't fit
smallest quant needs 166.1 GB
Mac 128 GB
Mac Studio M4 Max · Macs
DeepSeek V4 Flash 0731
Q2_K_S · ~27 tok/s
122.2 GB · up to 128Kfits
Inkling 2 Small
Doesn't fit
smallest quant needs 166.1 GB
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
DeepSeek V4 Flash 0731
Inkling 2 Small
Coding
DeepSeek V4 Flash 0731
Inkling 2 Small
no data
Math
DeepSeek V4 Flash 0731
Inkling 2 Small
no data
Science
DeepSeek V4 Flash 0731
Inkling 2 Small
no data
Reasoning
DeepSeek V4 Flash 0731
Inkling 2 Small
DeepSeek V4 Flash 0731 · #11 of 107 open models · #4 of 83 that fit ≤192 GB
Inkling 2 Small · #2 of 107 open models · #1 of 103 that fit ≤512 GB
Benchmarks
3 shared boards: DeepSeek V4 Flash 0731 leads 0, Inkling 2 Small leads 3 · Benchmarks imported Nov 2026
DeepSeek V4 Flash 0731
61.4%#5/23 open
IndependentEpoch AI · Jul 2026
Inkling 2 Small
81.7%#1/23 open
IndependentEpoch AI · Nov 2026
DeepSeek V4 Flash 0731
49.9%#19/74 open
Lab-reportedEpoch AI · Jul 2026
Inkling 2 Small
52.3%#10/74 open
Lab-reportedEpoch AI · Nov 2026
DeepSeek V4 Flash 0731
89.0%#7/23 open
IndependentEpoch AI · Jul 2026
Inkling 2 Small
96.5%#1/23 open
IndependentEpoch AI · Nov 2026
21 more boards (other shared and single-model boards)
Only DeepSeek V4 Flash 0731 (18)
- GPQA Diamond91.0%
- LiveBench Coding75.0
- LiveBench Reasoning86.6
- AIME 2024/202594.4%
- FrontierMath57.5%
- LiveBench Math86.8
- SimpleQA33.6%
- SimpleBench61.1%
- FrontierMath Tier 424.4%
- WeirdML63.0%
- FrontierCode18.8%
- Chess Puzzles32.0%
- CritPt16.6%
- DTBench90.9%
- LMCA41.7%
- Mystery Game Puzzles34.0%
- ALE-Bench1306.1
- ProofBench56.0%
Only Inkling 2 Small (3)
- LMArena Text1411.8
- LMArena WebDev1647.1
- APEX-Agents46.8%
VRAM by quantization
Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.
Q2_K
DeepSeek V4 Flash 0731
130 GB~129.3 GB file
32K 130 GB · 128K 131 GB
Inkling 2 Small
253 GB~252.4 GB file
32K 258 GB · 128K 272 GB
Q3_K_M
DeepSeek V4 Flash 0731
149 GB128.1 GB file
32K 149 GB · 128K 150 GB
Inkling 2 Small
290 GB~289.6 GB file
32K 295 GB · 128K 309 GB
Q4_K_M
DeepSeek V4 Flash 0731
183 GB~182.5 GB file
32K 183 GB · 128K 184 GB
Inkling 2 Small
357 GB~356.4 GB file
32K 362 GB · 128K 376 GB
Q5_K_M
DeepSeek V4 Flash 0731
217 GB~216.7 GB file
32K 217 GB · 128K 218 GB
Inkling 2 Small
424 GB~423.2 GB file
32K 428 GB · 128K 443 GB
Q6_K
DeepSeek V4 Flash 0731
251 GB~250.9 GB file
32K 252 GB · 128K 253 GB
Inkling 2 Small
491 GB~490.1 GB file
32K 495 GB · 128K 510 GB
Q8_0
DeepSeek V4 Flash 0731
305 GB~304.2 GB file
32K 305 GB · 128K 306 GB
Inkling 2 Small
595 GB~594.0 GB file
32K 599 GB · 128K 614 GB
12 more quants
IQ2_XXS
DeepSeek V4 Flash 0731
84.0 GB90.9 GB file
32K 84.3 GB · 128K 85.4 GB
Inkling 2 Small
164 GB190.6 GB file
32K 168 GB · 128K 183 GB
IQ2_XS
DeepSeek V4 Flash 0731
91.6 GB85.1 GB file
32K 91.9 GB · 128K 93.0 GB
Inkling 2 Small
not listed
IQ2_S
DeepSeek V4 Flash 0731
95.4 GB93.4 GB file
32K 95.7 GB · 128K 96.8 GB
Inkling 2 Small
not listed
IQ2_M
DeepSeek V4 Flash 0731
103 GB90.9 GB file
32K 103 GB · 128K 104 GB
Inkling 2 Small
not listed
IQ3_XXS
DeepSeek V4 Flash 0731
118 GB104.2 GB file
32K 119 GB · 128K 120 GB
Inkling 2 Small
231 GB226.0 GB file
32K 235 GB · 128K 250 GB
Q2_K_S
DeepSeek V4 Flash 0731
122 GB98.6 GB file
32K 122 GB · 128K 123 GB
Inkling 2 Small
not listed
IQ3_XS
DeepSeek V4 Flash 0731
126 GB118.2 GB file
32K 126 GB · 128K 127 GB
Inkling 2 Small
not listed
IQ3_S
DeepSeek V4 Flash 0731
130 GB116.1 GB file
32K 130 GB · 128K 131 GB
Inkling 2 Small
not listed
IQ3_M
DeepSeek V4 Flash 0731
137 GB135.8 GB file
32K 138 GB · 128K 139 GB
Inkling 2 Small
not listed
IQ4_XS
DeepSeek V4 Flash 0731
164 GB136.7 GB file
32K 164 GB · 128K 165 GB
Inkling 2 Small
not listed
IQ4_NL
DeepSeek V4 Flash 0731
171 GB136.7 GB file
32K 172 GB · 128K 173 GB
Inkling 2 Small
not listed
BF16
DeepSeek V4 Flash 0731
609 GB~608.4 GB file
32K 609 GB · 128K 610 GB
Inkling 2 Small
1189 GB~1188.0 GB file
32K 1193 GB · 128K 1208 GB
DeepSeek V4 Flash 0731
Ollama · Q4_K_M
ollama run hf.co/unsloth/DeepSeek-V4-Flash-0731-GGUFInkling 2 Small
Ollama · Q4_K_M
ollama run hf.co/unsloth/Inkling-2-Small-GGUF| Spec | DeepSeek V4 Flash 0731 | Inkling 2 Small |
|---|---|---|
| Publisher | DeepSeek | Thinking Machines |
| Parameters | 304.2B | 594B |
| Active parameters | 27B per token | 17B per token |
| Architecture | DeepseekV4ForCausalLM | Inkling2ForConditionalGeneration |
| Context | 1M tokens | 1M tokens |
| Modalities | Chat | Vision, Chat |
| License | MIT | Apache 2.0 |
| Released | Jul 2026 | Nov 2026 |
Frequently Asked Questions
Which is better, DeepSeek V4 Flash 0731 or Inkling 2 Small?
Inkling 2 Small leads llmrun Score 134.7 to 127.6; neither fits 24 GB. Choose DeepSeek V4 Flash 0731 for lighter on memory; choose Inkling 2 Small for higher llmrun Score and stronger at reasoning.
Which needs less VRAM, DeepSeek V4 Flash 0731 or Inkling 2 Small?
At Q4_K_M, DeepSeek V4 Flash 0731 requires 182.8 GB while Inkling 2 Small needs 357.0 GB, making DeepSeek V4 Flash 0731 the easier model to run on your local setup.
Can I run DeepSeek V4 Flash 0731 or Inkling 2 Small on a 16 GB GPU?
DeepSeek V4 Flash 0731 does not fit (smallest quant needs 84.1 GB); Inkling 2 Small does not fit (smallest quant needs 166.1 GB).
Which has a longer context window, DeepSeek V4 Flash 0731 or Inkling 2 Small?
DeepSeek V4 Flash 0731 supports 1,048,576 tokens and Inkling 2 Small supports 1,048,576 tokens.