DiffusionGemma (Google)
C Tier · 6.8/10
Google DeepMind's experimental open-weights TEXT-DIFFUSION model (June 10, 2026) -- 26B MoE (3.8B active), Apache 2.0, generates 256-token blocks in parallel with bidirectional attention for up to 4x faster output (1,000+ tok/s on H100). Trades some quality vs Gemma 4 for raw speed
Score Breakdown
The Good and the Bad
What we like
- +Text diffusion instead of autoregression: generates 256-token blocks in parallel with bidirectional attention -- up to 4x faster generation, 1,000+ tok/s on a single H100, 700+ tok/s on RTX 5090
- +First open-weights text-diffusion model from a frontier lab at useful scale (26B MoE, 3.8B active) -- until now diffusion LLMs were research demos or closed previews
- +Apache 2.0 with day-one ecosystem support (Hugging Face, NVIDIA NIM, vLLM, MLX, llama.cpp) -- you can actually deploy it, not just read the paper
- +Latency profile is ideal for interactive local use: autocomplete, draft generation, agent inner-loops where tokens-per-second matters more than peak quality
What could be better
- −Quality trails Gemma 4 on standard benchmarks -- Google positions it as a speed play, not a flagship; don't swap it into quality-sensitive pipelines
- −Speedup is hardware-dependent: much weaker on Apple Silicon unified memory, and the parallel-decode advantage shrinks at high-QPS server batch sizes
- −Experimental release -- diffusion text models have different failure modes (block-level incoherence) and far less community tuning lore than autoregressive Gemma
- −No hosted API tier at launch -- self-host or NIM only, so casual users have no easy way to try it
Pricing
Self-hosted (open weights)
- ✓Apache 2.0 license -- commercial use permitted
- ✓Weights on Hugging Face; NVIDIA NIM container; Gemini Enterprise Model Garden
- ✓~18GB VRAM quantized -- runs on RTX 5090-class consumer hardware (700+ tok/s)
- ✓Works with vLLM, MLX, and llama.cpp
System Requirements
Hardware needed to self-host. Min = smallest viable setup (usually heavy quantization). Max = full-precision / production-grade.
| Model variant | Min | Max |
|---|---|---|
| DiffusionGemma 26B MoE (3.8B active)Speedup is strongest on dedicated-VRAM NVIDIA GPUs; Apple Silicon unified memory sees much smaller gains. | ~18 GB VRAM quantized (RTX 4090/5090 tier) | 1x H100 for 1,000+ tok/s full-speed decode |
Known Issues
- LAUNCH (2026-06-10): DiffusionGemma released as an experimental open model. 26B-total / 3.8B-active MoE, Apache 2.0, text-diffusion architecture generating 256-token blocks in parallel with bidirectional attention. Vendor-claimed speeds: up to 4x faster than comparable autoregressive models, 1,000+ tok/s on H100, 700+ tok/s on RTX 5090, ~18GB VRAM quantized. Availability: Hugging Face weights, NVIDIA NIM, Gemini Enterprise Model Garden; vLLM/MLX/llama.cpp support at launch. Google's own caveats: trails Gemma 4 on quality benchmarks; speed advantage weaker on Apple Silicon and in high-QPS serving. Front-page Hacker News reception (226 points) on launch daySource: Google blog (blog.google/innovation-and-ai/technology/developers-tools/diffusion-gemma-faster-text-generation/), Google developers blog (developers.googleblog.com/en/diffusiongemma-the-developer-guide/), NVIDIA blog (RTX AI Garage) · 2026-06-10
Best for
Developers who need fast local text generation -- autocomplete, drafting, high-volume agent inner-loops -- on a single GPU, and researchers who want a production-grade open diffusion LLM to build on.
Not for
Quality-first workloads (use Gemma 4 or a frontier API model), Mac-only setups (the speedup mostly evaporates on Apple Silicon), or anyone wanting a hosted try-before-you-deploy API -- there isn't one yet.
Our Verdict
DiffusionGemma is the most interesting open-weights release of June 2026 not because it's the best model -- Google openly says Gemma 4 beats it on quality -- but because it's the first serious, deployable text-diffusion LLM from a frontier lab. The 4x generation-speed claim holds on the right hardware (H100/RTX-class GPUs), which makes it a genuine option for latency-sensitive local work like autocomplete and agent inner-loops. Treat it as a speed specialist and an architecture preview: if diffusion decoding keeps scaling, this is what the next generation of local models may look like. For now, pair it with a quality model rather than replacing one.
Sources
- Google blog: DiffusionGemma -- faster text generation (2026-06-10) (accessed 2026-06-10)
- Google developers blog: DiffusionGemma developer guide (accessed 2026-06-10)
- NVIDIA blog: RTX AI Garage -- local Gemma Diffusion (accessed 2026-06-10)
- MarkTechPost: DiffusionGemma analysis (accessed 2026-06-10)
Explore more DiffusionGemma (Google) rankings
Deeper leaderboards, benchmarks, task-specific tier lists, and status/pricing pages for DiffusionGemma (Google).
The Tier List Tuesday
Weekly newsletter: tier movers, new entrants, and the VS of the week. Built from our daily AI-tool sweeps. No spam, unsubscribe anytime.
Alternatives to DiffusionGemma (Google)
Llama 4 (Meta)
Meta's open-weights family -- Scout (10M context), Maverick (multimodal 400B MoE). NOTE: Meta's frontier work moved to the proprietary Muse Spark line in April 2026; Llama remains downloadable and supported but is effectively in maintenance mode
Mistral AI
European AI lab with open and commercial models -- Le Chat is now **Vibe** (May 28 2026): one agent across Work Mode + Code Mode with a VS Code extension and CLI, powered by Mistral Medium 3.5 (128B dense, 256k context, 77.6% SWE-Bench Verified). Earlier 2026 line: Small 4 (119B MoE Apache 2.0), Medium 3, Voxtral TTS
DeepSeek
DeepSeek V4 shipped 2026-04-24: V4-Pro (1.6T/49B active MoE) + V4-Flash (284B/13B active), 1M native context, Hybrid Attention Architecture, open-source on HF. Trails only Gemini 3.1 Pro on world knowledge
Gemma 4 (Google)
Google DeepMind's open-weights model family -- multimodal, 256K context, runs on edge devices
Qwen (Alibaba)
Alibaba's open-weights + API family -- Qwen3.8-Max flagship previewed at WAIC (Jul 19 2026: 2.4T sparse-MoE multimodal, closed preview, 'second only to Fable 5'), Qwen 3.7 Max GA (SWE-Bench Pro 60.6%, Terminal-Bench 69.7%, $2.50/$7.50 per 1M), Qwen3.6-27B dense Apache 2.0 (beats the 397B MoE on coding from one consumer GPU)
GLM / Z.ai (Zhipu AI)
Zhipu AI's open-weights flagship -- GLM-5.2 (launched 2026-06-13) is a ~753B-parameter MoE with a 1M-token context and the new IndexShare sparse-attention architecture (~2.9x lower per-token FLOPs at 1M context), MIT licensed. Vendor benchmarks put SWE-Bench Pro at 62.1 (up from GLM-5.1's 58.4) and it tops the Artificial Analysis open-weights Intelligence Index; VentureBeat reports it beats GPT-5.5 on several long-horizon coding benchmarks at roughly 1/6 the cost. Drop-in for Claude Code / Cline / OpenCode. Still trained outside the Nvidia stack on Huawei Ascend silicon
Kimi K3 (Moonshot)
Moonshot's 2.8T-parameter Kimi K3 (launched 2026-07-16/17) is the largest open-weight model ever announced -- 1M context, multimodal, $3/$15 per 1M via API, ranked best-available on Arena.AI at launch. Weights promised late July (press cites 7/27); K2.6/K2.7-Code remain the shipped-weights line
Nemotron (Nvidia)
Nvidia's open-weights family -- hybrid Mamba-Transformer MoE architecture, optimized for efficient reasoning on Nvidia hardware. Nemotron 3 Ultra (550B total / 55B active) shipped 2026-06-04 as the family flagship, joining Super (120B/12B, March) and Nano
MiniMax M3
MiniMax's coding/agent flagship -- M3 (June 1 2026): 1M-token context, MSA sparse attention (>15x decoding speedup at long context), SWE-Bench Pro 59.0%, Terminal-Bench 66.0%. OPEN WEIGHTS LIVE on HuggingFace since June 12 (~428B total / ~23B active, native multimodal, minimax-community license)
Falcon (TII)
UAE's Technology Innovation Institute open-weights family -- Falcon 3 optimized for efficient sub-10B deployment on consumer hardware
gpt-oss (OpenAI)
OpenAI's FIRST open-weight models -- gpt-oss-120b (single 80GB GPU, near parity with o4-mini on reasoning) and gpt-oss-20b (runs on 16GB edge devices). Apache 2.0. Launched 2025-08-05. gpt-oss-safeguard ships in 2026 as the safety-tuned variant
IBM Granite 4.0
IBM's enterprise-focused open-weight family -- Granite 4.0 hybrid Mamba-2 + transformer architecture (70-80% memory reduction vs pure transformer), 3B to 32B sizes, Apache 2.0. First open model family to secure ISO 42001 certification. Nano 350M runs on CPU with 8-16GB RAM. 3B Vision variant landed 2026-04-01
Arcee Trinity-Large-Thinking
Arcee AI's US-made open-weight frontier reasoning model -- launched 2026-04-01. 398B total params, ~13B active. Sparse MoE (256 experts, 4 active = 1.56% routing). Apache 2.0, trained from scratch. #2 on PinchBench trailing only Claude 3.5 Opus. ~96% cheaper than Opus-4.6 on agentic tasks
Olmo 3 (AI2)
Allen Institute for AI's fully-open frontier reasoning models -- Olmo 3 family (2025-11-20) includes 7B and 32B sizes, four variants (Base, Think, Instruct, RLZero). Apache 2.0 with fully open data + checkpoints + training logs. Olmo 3-Think 32B matches Qwen3-32B-Thinking at 6x fewer training tokens
AI21 Jamba2
AI21 Labs' hybrid SSM-Transformer (Mamba-style) open-weight family -- Jamba2 launched 2026-01-08. Two sizes: 3B dense (runs on phones / laptops) and Jamba2 Mini MoE (12B active / 52B total). Apache 2.0, 256K context, mid-trained on 500B tokens
StepFun Step 3.7 Flash
StepFun's (China) agent-focused open-weight family -- Step 3.7 Flash (May 28 2026): 198B sparse MoE vision-language model, ~11B active, 256K context, Apache 2.0, ~400 tok/s, SWE-Bench Pro 56.3. Supersedes Step 3.5 Flash (Feb 2026) as the flagship
Cohere Command A
Cohere's enterprise-multilingual flagship -- 111B params, 256K context, runs on 2x H100. 23 languages. CC-BY-NC 4.0 on weights (research / non-commercial), commercial requires Cohere enterprise contract. Follow-ups: Command A Reasoning + Command A Vision
LongCat-2.0 (Meituan)
Meituan's open-source 1.6T-parameter MoE (~48B active) with native 1M-token context, MIT license -- trained entirely on domestic Chinese AI ASICs and revealed as the stealth 'Owl Alpha' model that had been topping OpenRouter
Inkling (Thinking Machines Lab)
Mira Murati's $12B lab ships its first model (2026-07-15): a 975B/41B-active open-weights MoE that reasons natively over text, images, and audio with a 1M-token context -- positioned not as the strongest model, but as the best starting point for fine-tuning via Tinker
Bonsai 27B (PrismML)
The first 27B-class model that runs on a phone (2026-07-14) -- ternary and 1-bit quantizations of Qwen3.6 27B squeeze a multimodal, tool-calling, 262K-context model into 3.9-5.9GB under Apache 2.0