Rnj-1 Instruct

Essential AI · essentialai/rnj-1-instruct

ProviderEssential AI
Familyrnj
Typellm-code
Statusactive
Released2025-12-08
Updated2025-12-24
Parameters8.3B
Open weightsyes

Lineage

RelationshipModel
Is a finetune ofEssentialAI/rnj-1

Capabilities

Function Calling · tier-2

What it fits on

Ordered by predicted speed. Bandwidth sets decode rate; memory decides whether it runs at all.

Every figure here is computed, not measured. Fit is weights at each quantisation against device memory, with a 25% allowance for the KV cache, activations and the OS. Decode rate is the memory-bandwidth roofline at 70% efficiency. Nobody has run this model on these devices.
DeviceMemoryBandwidthBest qualityWeightstok/sFastest
Cerebras WSE-344.0 GB21000000.0 GB/sbf1616.62 GB~884423.2~3537692.7 q4
NVIDIA GB200 Grace Blackwell Superchip372.0 GB16000.0 GB/sbf1616.62 GB~673.8~2695.4 q4
AMD Instinct MI355X288.0 GB8000.0 GB/sbf1616.62 GB~336.9~1347.7 q4
NVIDIA B200180.0 GB7700.0 GB/sbf1616.62 GB~324.3~1297.2 q4
Google TPU7x (Ironwood)192.0 GB7380.0 GB/sbf1616.62 GB~310.8~1243.2 q4
AMD Instinct MI325X256.0 GB6000.0 GB/sbf1616.62 GB~252.7~1010.8 q4
AMD Instinct MI300X192.0 GB5300.0 GB/sbf1616.62 GB~223.2~892.8 q4
NVIDIA H200 SXM141.0 GB4800.0 GB/sbf1616.62 GB~202.2~808.6 q4
NVIDIA H100 NVL94.0 GB3900.0 GB/sbf1616.62 GB~164.3~657.0 q4
NVIDIA H100 SXM80.0 GB3350.0 GB/sbf1616.62 GB~141.1~564.3 q4
AMD Instinct MI250X128.0 GB3200.0 GB/sbf1616.62 GB~134.8~539.1 q4
Google TPU v5p95.0 GB2765.0 GB/sbf1616.62 GB~116.4~465.8 q4
NVIDIA A100 80GB SXM80.0 GB2039.0 GB/sbf1616.62 GB~85.9~343.5 q4
NVIDIA H100 PCIe80.0 GB2000.0 GB/sbf1616.62 GB~84.2~336.9 q4
NVIDIA GeForce RTX 509032.0 GB1792.0 GB/sbf1616.62 GB~75.5~301.9 q4
Google TPU v6e (Trillium)32.0 GB1638.0 GB/sbf1616.62 GB~69.0~275.9 q4
AMD Instinct MI21064.0 GB1600.0 GB/sbf1616.62 GB~67.4~269.5 q4
NVIDIA A100 40GB SXM40.0 GB1555.0 GB/sbf1616.62 GB~65.5~262.0 q4
Google TPU v432.0 GB1200.0 GB/sbf1616.62 GB~50.5~202.2 q4
NVIDIA GeForce RTX 409024.0 GB1008.0 GB/sbf1616.62 GB~42.5~169.8 q4
AMD Radeon RX 7900 XTX24.0 GB960.0 GB/sbf1616.62 GB~40.4~161.7 q4
NVIDIA GeForce RTX 508016.0 GB960.0 GB/sfp88.31 GB~80.9~161.7 q4
NVIDIA GeForce RTX 309024.0 GB936.0 GB/sbf1616.62 GB~39.4~157.7 q4
NVIDIA L40S48.0 GB864.0 GB/sbf1616.62 GB~36.4~145.6 q4
Apple M3 Ultra512.0 GB819.0 GB/sbf1616.62 GB~34.5~138.0 q4
AMD Radeon RX 7900 XT20.0 GB800.0 GB/sfp88.31 GB~67.4~134.8 q4
Apple M2 Ultra192.0 GB800.0 GB/sbf1616.62 GB~33.7~134.8 q4
Google TPU v5e16.0 GB800.0 GB/sfp88.31 GB~67.4~134.8 q4
NVIDIA GeForce RTX 4080 SUPER16.0 GB736.0 GB/sfp88.31 GB~62.0~124.0 q4
NVIDIA GeForce RTX 4070 Ti SUPER16.0 GB672.0 GB/sfp88.31 GB~56.6~113.2 q4
AMD Radeon RX 9070 XT16.0 GB640.0 GB/sfp88.31 GB~53.9~107.8 q4
Apple M4 Max128.0 GB546.0 GB/sbf1616.62 GB~23.0~92.0 q4
Apple M1 Max64.0 GB400.0 GB/sbf1616.62 GB~16.8~67.4 q4
Apple M2 Max96.0 GB400.0 GB/sbf1616.62 GB~16.8~67.4 q4
Apple M3 Max128.0 GB400.0 GB/sbf1616.62 GB~16.8~67.4 q4
NVIDIA GeForce RTX 3060 12GB12.0 GB360.0 GB/sfp88.31 GB~30.3~60.6 q4
NVIDIA L424.0 GB300.0 GB/sbf1616.62 GB~12.6~50.5 q4
NVIDIA GeForce RTX 4060 Ti 16GB16.0 GB288.0 GB/sfp88.31 GB~24.3~48.5 q4
Apple M4 Pro64.0 GB273.0 GB/sbf1616.62 GB~11.5~46.0 q4
Apple M432.0 GB120.0 GB/sbf1616.62 GB~5.1~20.2 q4

Where it runs

Taken from the card's availability section.

PlatformId on that platform
Hugging FaceEssentialAI/rnj-1-instruct
LM Studiornj-1
Ollamarnj-1
OpenRouteressentialai/rnj-1-instruct
Together AIessentialai/rnj-1-instruct

Reported benchmark scores

This card reports no benchmark scores yet.

BenchmarkCatalogue standingScore

Data

This card as JSON · See it in the graph · Edit on GitHub