Quick:
nearai
Active
Dense
Gemma 4 31B IT
Model Spec
nearai:google/gemma-4-31B-it
Modalities
Input
text
Output
text
Capabilities
Chat
Reasoning
Tools
Streaming
Pricing Components
| Component | Price | Conditions | Source |
|---|---|---|---|
| token.input | $0.13 / 1M tokens | Standard | — |
| token.output | $0.40 / 1M tokens | Standard | — |
| token.cache_read | $0.03 / 1M tokens | Standard | — |
Specifications
Architecture
Dense
Total Parameters
32.7B
Active Parameters
N/A
Minimum RAM
18.3 GB
Minimum VRAM
16.7 GB
Context Window
262,144 tokens
Max Output
32,768 tokens
Input Cost
$0.13/M
Output Cost
$0.40/M
History
Raw JSONTimeline is based on collected llm_db history snapshots and may be incomplete.
2026-07-14
changed
-
catalog_only
(remove)
true → —
-
execution
(add)
— → {2 fields}
-
extra.llmfit.memory.min_ram_gb
(replace)
18.3 → 17.3
2026-07-02
changed
-
extra.description
(add)
— → Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
2026-06-25
changed
-
extra.llmfit.hf_downloads
(replace)
11081369 → 11333838
-
extra.llmfit.hf_likes
(replace)
3031 → 3052
2026-06-24
changed
-
extra.llmfit.hf_downloads
(replace)
10283716 → 11081369
-
extra.llmfit.hf_likes
(replace)
2735 → 3031
-
extra.llmfit.use_case
(replace)
General purpose → Multimodal, vision and text
2026-06-15
changed
-
extra.reasoning_options
(add)
— → [1 items]
2026-05-24
changed
-
extra.llmfit.gguf_sources
(replace)
[0 items] → [3 items]
-
extra.llmfit.hf_downloads
(replace)
9851216 → 10283716
-
extra.llmfit.hf_likes
(replace)
2660 → 2735
2026-05-23
introduced
snapshots 64bf744 -> b7ca903 • generated 2026-08-05T03:31:59
See incorrect model data? Help us improve it.
Submit Fix on GitHub
6293
of 6427 models
1 / 126
Page 1 of 126