Models the long tail · browse the live catalog
Umbra's coordinator is unreachable right now — data may be stale. Retry ×
All Llama Qwen Mixtral Uncensored Coding
Models available through Umbra Start with models serving from the provider network now. The broader catalog stays below for discovery, request planning, and models waiting for capacity.
available = serving at the latest live check more models = approved catalog entries without current capacity tok/s live = measured from providers now
try one in playground →
Available and working now 3 These are the first models to try: the coordinator reported active serving capacity at the latest check.
serving nowhf-empero-ai-qwythos-9b-claude-mythos-5-1m-gguf-qwythos-9b-claude-mythos-5-1m-mtp-q4-k-m
qwen35 Q4_K_M 16 GB digest pinned
$0.10/M in
$0.30/M out
~13 tok/s live repo empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF rev e62b0367 license apache-2.0
hf-liquidai-lfm2.5-230m-gguf-lfm2-5-230m-q4-k-m
lfm2 Q4_K_M 8 GB digest pinned
$0.03/M in
$0.10/M out
~34 tok/s live repo LiquidAI/LFM2.5-230M-GGUF rev fa224d4c license other
hf-yuxinlu1-gemma-4-12b-coder-fable5-composer2.5-v1-gguf-gemma4-coding-q4-k-m
gemma4 Q4_K_M 9 GB digest pinned
$0.20/M in
$0.60/M out
~51 tok/s est repo yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF rev 1380be17 license apache-2.0
More models in the catalog 9 Approved public models with no current serving capacity. Availability can change as providers come online.
hf-deepreinforce-ai-ornith-1.0-35b-gguf-ornith-1-0-35b-q4-k-m
qwen35moe Q4_K_M 23 GB digest pinned
$0.40/M in
$1.20/M out
~17 tok/s est repo deepreinforce-ai/Ornith-1.0-35B-GGUF rev c2e17030 license mit
hf-deepreinforce-ai-ornith-1.0-9b-gguf-ornith-1-0-9b-q4-k-m
qwen35 Q4_K_M 8 GB digest pinned
$0.10/M in
$0.30/M out
~67 tok/s est repo deepreinforce-ai/Ornith-1.0-9B-GGUF rev 3296bc7a license mit
hf-hauhaucs-qwen3.6-35b-a3b-uncensored-hauhaucs-aggressive-qwen3-6-35b-a3b-uncensored-hauhaucs-aggressive-q4-k-m
qwen35moe Q4_K_M 23 GB digest pinned
$0.40/M in
$1.20/M out
~202 tok/s est repo HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive rev f12a584f license apache-2.0
hf-liquidai-lfm2.5-230m-gguf-lfm2-5-230m-bf16
lfm2 Q4_0_4_4 8 GB digest pinned
$0.03/M in
$0.10/M out
~300 tok/s est repo LiquidAI/LFM2.5-230M-GGUF rev fa224d4c license other
hf-liquidai-lfm2.5-230m-gguf-lfm2-5-230m-q8-0
lfm2 Q8_0 8 GB digest pinned
$0.03/M in
$0.10/M out
~300 tok/s est repo LiquidAI/LFM2.5-230M-GGUF rev fa224d4c license other
hf-qwen-qwen2.5-0.5b-instruct-gguf-qwen2-5-0-5b-instruct-fp16
qwen2 F16 8 GB digest pinned
$0.03/M in
$0.10/M out
~36 tok/s est repo Qwen/Qwen2.5-0.5B-Instruct-GGUF rev 9217f5db license apache-2.0
hf-qwen-qwen3-8b-gguf-qwen3-8b-q4-k-m
qwen3 Q4_K_M 8 GB digest pinned
$0.10/M in
$0.30/M out
~76 tok/s est repo Qwen/Qwen3-8B-GGUF rev 7c41481f license apache-2.0
hf-thebloke-tinyllama-1.1b-chat-v1.0-gguf-tinyllama-1-1b-chat-v1-0-q2-k
llama Q2_K 8 GB digest pinned
$0.10/M in
$0.30/M out
~300 tok/s est repo TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF rev 52e7645b license apache-2.0
hf-unsloth-gemma-3-4b-it-gguf-gemma-3-4b-it-q4-k-m
gemma3 Q4_K_M 8 GB digest pinned
$0.10/M in
$0.30/M out
~152 tok/s est repo unsloth/gemma-3-4b-it-GGUF rev 5a3566e7 license gemma
Continue related in the console